From 70c10e4aa471e2d9e7bc46c8275674bc1839aaaf Mon Sep 17 00:00:00 2001 From: Jack Ye Date: Fri, 25 Sep 2026 15:19:54 -0700 Subject: [PATCH] docs: own every page path, and port the upstream changes lancedb now holds a page at every path the site publishes, including the twelve Enterprise ones. Those are real open-source pages -- what the capability is, and what the embedded form does instead -- rather than blank placeholders, so the open-source site is complete on its own. sophon becomes an overlay whose page replaces the one at the same path, which means navigation lives in one place and the two repositories only have to agree on a path. That removes the whole class of problem where a page could only be reached from one of the two trees. The open-source site went from twenty-four dangling Enterprise links to one, and that one points at the dataset pages the build repository owns. Ports four changes that landed on the docs repository after this branch left it: #344 indexing and quantization rewritten #354 LeRobot native reader #361 training/index renamed to training/data-loading and rewritten #362 distance metric mismatch falls back to a brute-force scan None applied as patches, because these files were merged or split here -- quantization into the vector index page, multi-vector into vector search, performance into four pages. Each was ported by taking the upstream page and re-applying the restructure on top, which also picked up a correction that would otherwise have been lost: the stricter brute-force threshold for multi-vector columns is a Cloud limit, not an Enterprise one. The upstream LeRobot page linked to a Geneva page that no longer exists; it now points at the feature-engineering pages that replaced it. --- docs/web/curation/index.mdx | 2 +- docs/web/curation/sampling.mdx | 2 +- docs/web/docs.json | 35 +- docs/web/enterprise/architecture.mdx | 20 + docs/web/enterprise/authentication.mdx | 26 + docs/web/enterprise/benchmarks.mdx | 20 + docs/web/enterprise/deployment/azure.mdx | 17 + docs/web/enterprise/deployment/index.mdx | 20 + docs/web/enterprise/index.mdx | 29 + docs/web/enterprise/security.mdx | 20 + docs/web/faq/faq-enterprise.mdx | 19 + docs/web/governance/authorization.mdx | 26 + docs/web/index.mdx | 2 +- docs/web/indexing/index.mdx | 154 +---- docs/web/indexing/scalar-index.mdx | 42 +- docs/web/indexing/vector-index.mdx | 553 ++++++++---------- docs/web/integrations/lerobotdataset.mdx | 165 ++++-- docs/web/management/view.mdx | 32 + docs/web/quickstart.mdx | 4 +- docs/web/search/sql/fts-sql.mdx | 32 + docs/web/search/sql/index.mdx | 29 + docs/web/search/vector-search.mdx | 111 ++-- docs/web/snippets/indexing.mdx | 16 +- docs/web/snippets/integrations.mdx | 6 +- docs/web/sql/sampling.mdx | 2 +- .../images/indexing/hnsw_layered_graph.png | Bin 0 -> 58243 bytes .../integrations/lerobot-foxglove-droid.png | Bin 0 -> 572468 bytes docs/web/static/styles/style.css | 14 + docs/web/training/data-loading.mdx | 475 +++++++++++++++ docs/web/training/index.mdx | 512 ---------------- docs/web/training/object-detection.mdx | 4 +- docs/web/training/torch.mdx | 2 +- docs/web/training/why-lancedb.mdx | 2 +- docs/web/tutorials/index.mdx | 2 +- 34 files changed, 1292 insertions(+), 1103 deletions(-) create mode 100644 docs/web/enterprise/architecture.mdx create mode 100644 docs/web/enterprise/authentication.mdx create mode 100644 docs/web/enterprise/benchmarks.mdx create mode 100644 docs/web/enterprise/deployment/azure.mdx create mode 100644 docs/web/enterprise/deployment/index.mdx create mode 100644 docs/web/enterprise/index.mdx create mode 100644 docs/web/enterprise/security.mdx create mode 100644 docs/web/faq/faq-enterprise.mdx create mode 100644 docs/web/governance/authorization.mdx create mode 100644 docs/web/management/view.mdx create mode 100644 docs/web/search/sql/fts-sql.mdx create mode 100644 docs/web/search/sql/index.mdx create mode 100644 docs/web/static/assets/images/indexing/hnsw_layered_graph.png create mode 100644 docs/web/static/assets/images/integrations/lerobot-foxglove-droid.png create mode 100644 docs/web/training/data-loading.mdx delete mode 100644 docs/web/training/index.mdx diff --git a/docs/web/curation/index.mdx b/docs/web/curation/index.mdx index 216149c71..09f7aa851 100644 --- a/docs/web/curation/index.mdx +++ b/docs/web/curation/index.mdx @@ -51,4 +51,4 @@ you ended up with. A curated result you want to keep is a [materialized view](/management/materialized-view) -- stored, refreshed, and -readable by a [data loader](/training) like any other table. +readable by a [data loader](/training/data-loading) like any other table. diff --git a/docs/web/curation/sampling.mdx b/docs/web/curation/sampling.mdx index f38517379..a2c1289b3 100644 --- a/docs/web/curation/sampling.mdx +++ b/docs/web/curation/sampling.mdx @@ -90,7 +90,7 @@ dataloader = torch.utils.data.DataLoader(permutation) This is the right tool for epoch-level shuffling, where you want every row eventually and only the order varies. `TABLESAMPLE` is for when you want fewer -rows. See [Training](/training). +rows. See [Training](/training/data-loading). ## Reference {#reference} diff --git a/docs/web/docs.json b/docs/web/docs.json index 3a152537d..ef0635e85 100644 --- a/docs/web/docs.json +++ b/docs/web/docs.json @@ -134,6 +134,10 @@ { "source": "/reranking/:slug*", "destination": "/reranking" + }, + { + "source": "/training", + "destination": "/training/data-loading" } ], "navigation": { @@ -209,7 +213,7 @@ "group": "Training", "pages": [ "training/why-lancedb", - "training/index", + "training/data-loading", "training/torch" ] }, @@ -222,6 +226,7 @@ "management/table", "tables/branching", "management/materialized-view", + "management/view", "management/function" ] }, @@ -249,12 +254,37 @@ } ] }, + { + "group": "Security", + "pages": [ + "enterprise/authentication", + "governance/authorization", + "enterprise/security" + ] + }, + { + "group": "Deployment", + "pages": [ + "enterprise/index", + "enterprise/architecture", + { + "group": "Cloud Providers", + "pages": [ + "enterprise/deployment/index", + "enterprise/deployment/azure" + ] + }, + "enterprise/benchmarks" + ] + }, { "group": "SQL Reference", "pages": [ "sql/index", + "search/sql/index", "sql/data-types", "sql/select", + "search/sql/fts-sql", "sql/subqueries", "sql/join", "sql/aggregation", @@ -279,7 +309,8 @@ "group": "FAQ", "pages": [ "faq/index", - "faq/faq-oss" + "faq/faq-oss", + "faq/faq-enterprise" ] } ] diff --git a/docs/web/enterprise/architecture.mdx b/docs/web/enterprise/architecture.mdx new file mode 100644 index 000000000..fc1c1c7db --- /dev/null +++ b/docs/web/enterprise/architecture.mdx @@ -0,0 +1,20 @@ +--- +title: "Enterprise architecture" +sidebarTitle: "Architecture" +description: "The tiers a deployment runs, and how they scale independently." +icon: cubes +keywords: ["architecture", "control plane", "data plane", "indexer"] +--- + +Enterprise + +This page describes a LanceDB Enterprise capability. The embedded form +of LanceDB has no server to provide it -- see +[Architecture](/architecture) for what differs between the two. + +A deployment separates compute from storage so each scales on its own: table +data and indexes live in object storage, while query serving and background work +run on machines that can be replaced without any of them owning the data. + +[Architecture](/architecture) covers this alongside the embedded form, which is +the comparison most readers want first. diff --git a/docs/web/enterprise/authentication.mdx b/docs/web/enterprise/authentication.mdx new file mode 100644 index 000000000..e07d9b3bd --- /dev/null +++ b/docs/web/enterprise/authentication.mdx @@ -0,0 +1,26 @@ +--- +title: "Authentication" +sidebarTitle: "Authentication" +description: "Establishing who is calling: API keys and identity provider integration." +icon: key +keywords: ["authentication", "api key", "oidc", "identity"] +--- + +Enterprise + +This page describes a LanceDB Enterprise capability. The embedded form +of LanceDB has no server to provide it -- see +[Architecture](/architecture) for what differs between the two. + +A deployment authenticates every request before +[authorization](/governance/authorization) decides what it may do. + +```python +db = lancedb.connect("db://my-database", api_key="...", region="us-east-1") +``` + +An API key belongs in the environment rather than in source. See +[Database](/management/database#deployment) for the connection options. + +Embedded LanceDB has nothing to authenticate to -- your process opens the files +directly, and the object store's own credentials are the only gate. diff --git a/docs/web/enterprise/benchmarks.mdx b/docs/web/enterprise/benchmarks.mdx new file mode 100644 index 000000000..3626f7b81 --- /dev/null +++ b/docs/web/enterprise/benchmarks.mdx @@ -0,0 +1,20 @@ +--- +title: "Benchmarks" +sidebarTitle: "Benchmarks" +description: "Published performance results for LanceDB Enterprise." +icon: chart-line +keywords: ["benchmarks", "performance", "throughput", "latency"] +--- + +Enterprise + +This page describes a LanceDB Enterprise capability. The embedded form +of LanceDB has no server to provide it -- see +[Architecture](/architecture) for what differs between the two. + +Benchmark results are specific to a deployment's shape -- cluster size, storage +class, dataset -- so they are published with LanceDB Enterprise. + +For tuning your own workload rather than comparing published numbers, see +[Query plans](/search/explain) and the performance notes on +[Search](/search#performance) and [Insert](/ingestion/insert#performance). diff --git a/docs/web/enterprise/deployment/azure.mdx b/docs/web/enterprise/deployment/azure.mdx new file mode 100644 index 000000000..a045e6204 --- /dev/null +++ b/docs/web/enterprise/deployment/azure.mdx @@ -0,0 +1,17 @@ +--- +title: "Azure deployment guide" +sidebarTitle: "Azure" +description: "Deploying LanceDB Enterprise on Azure." +icon: cloud +keywords: ["azure", "deployment", "aks"] +--- + +Enterprise + +This page describes a LanceDB Enterprise capability. The embedded form +of LanceDB has no server to provide it -- see +[Architecture](/architecture) for what differs between the two. + +The Azure deployment procedure is published with LanceDB Enterprise. See +[Deployment](/enterprise/deployment) for the general shape, and +[contact us](mailto:contact@lancedb.com) to get started. diff --git a/docs/web/enterprise/deployment/index.mdx b/docs/web/enterprise/deployment/index.mdx new file mode 100644 index 000000000..3002cc844 --- /dev/null +++ b/docs/web/enterprise/deployment/index.mdx @@ -0,0 +1,20 @@ +--- +title: "Deployment guide" +sidebarTitle: "Overview" +description: "Standing up a LanceDB Enterprise deployment." +icon: server +keywords: ["deployment", "install", "cluster", "kubernetes"] +--- + +Enterprise + +This page describes a LanceDB Enterprise capability. The embedded form +of LanceDB has no server to provide it -- see +[Architecture](/architecture) for what differs between the two. + +Deployment is specific to your cloud and account, so the procedure is published +with LanceDB Enterprise. [Contact us](mailto:contact@lancedb.com) to get +started. + +Embedded LanceDB has nothing to deploy -- it is a library your process links +against. See [Architecture](/architecture#embedded). diff --git a/docs/web/enterprise/index.mdx b/docs/web/enterprise/index.mdx new file mode 100644 index 000000000..ed4d232c1 --- /dev/null +++ b/docs/web/enterprise/index.mdx @@ -0,0 +1,29 @@ +--- +title: "LanceDB Enterprise" +sidebarTitle: "Overview" +description: "What a deployment adds over embedded LanceDB." +icon: building +keywords: ["enterprise", "deployment", "cluster"] +--- + +Enterprise + +This page describes a LanceDB Enterprise capability. The embedded form +of LanceDB has no server to provide it -- see +[Architecture](/architecture) for what differs between the two. + +LanceDB Enterprise runs the lakehouse as a service: a control plane for +configuration, identity and policy; a data plane serving reads and writes; and +indexers building indexes and compacting outside the request path. + +What it adds over the embedded form: + +| | | +| --- | --- | +| [SQL](/sql) | an Arrow Flight SQL endpoint | +| [Functions](/management/function) | Python running on workers | +| [Jobs](/basics/jobs) | server-side work with ids, status and events | +| [Authorization](/governance/authorization) | per-object grants | +| Scale | a cluster rather than your process | + +See [Architecture](/architecture) for the two shapes side by side. diff --git a/docs/web/enterprise/security.mdx b/docs/web/enterprise/security.mdx new file mode 100644 index 000000000..a2b60a242 --- /dev/null +++ b/docs/web/enterprise/security.mdx @@ -0,0 +1,20 @@ +--- +title: "Compliance" +sidebarTitle: "Compliance" +description: "Certifications, data handling, and the controls a deployment provides." +icon: certificate +keywords: ["compliance", "security", "soc2", "encryption", "audit"] +--- + +Enterprise + +This page describes a LanceDB Enterprise capability. The embedded form +of LanceDB has no server to provide it -- see +[Architecture](/architecture) for what differs between the two. + +Compliance posture -- certifications, data residency, encryption at rest and in +transit, audit logging -- is a property of a deployment, so it is documented +with LanceDB Enterprise. + +For embedded LanceDB, these are properties of the object store you point it at +and the process you run it in; LanceDB adds no layer of its own. diff --git a/docs/web/faq/faq-enterprise.mdx b/docs/web/faq/faq-enterprise.mdx new file mode 100644 index 000000000..60c2132f2 --- /dev/null +++ b/docs/web/faq/faq-enterprise.mdx @@ -0,0 +1,19 @@ +--- +title: "LanceDB Enterprise FAQ" +sidebarTitle: "LanceDB Enterprise" +description: "Common questions about running LanceDB Enterprise." +icon: circle-question +keywords: ["faq", "enterprise"] +--- + +Enterprise + +This page describes a LanceDB Enterprise capability. The embedded form +of LanceDB has no server to provide it -- see +[Architecture](/architecture) for what differs between the two. + +Questions specific to running a deployment are answered with LanceDB +Enterprise. + +For questions about the embedded form, see the +[LanceDB OSS FAQ](/faq/faq-oss). diff --git a/docs/web/governance/authorization.mdx b/docs/web/governance/authorization.mdx new file mode 100644 index 000000000..c19914908 --- /dev/null +++ b/docs/web/governance/authorization.mdx @@ -0,0 +1,26 @@ +--- +title: "Authorization" +sidebarTitle: "Authorization" +description: "Who may do what: privileges granted on catalog objects to principals, groups, roles, and API keys." +icon: shield-halved +keywords: ["authorization", "authz", "privileges", "rbac", "access control"] +--- + +Enterprise + +This page describes a LanceDB Enterprise capability. The embedded form +of LanceDB has no server to provide it -- see +[Architecture](/architecture) for what differs between the two. + +[Authentication](/enterprise/authentication) establishes who is calling. +Authorization decides what they may do. + +An access control entry grants **one privilege** on **one object** to **one +subject**. Objects are addressed by kind and path -- `system`, `database:db`, +`namespace:db/ns`, `table:db/ns/table` -- and the hierarchy is not decorative: +reaching a table requires `USAGE` on the namespace containing it and on the +database containing that. + +Embedded LanceDB has no such layer. Access is whatever the object store +enforces on the bucket or directory, which is coarser and has no concept of a +table. diff --git a/docs/web/index.mdx b/docs/web/index.mdx index 807cff9f8..86bbf9e5c 100644 --- a/docs/web/index.mdx +++ b/docs/web/index.mdx @@ -61,7 +61,7 @@ feature engineering, search and retrieval, and efficient training data access. Learn why LanceDB works well as the data layer for training workloads. - + Use LanceDB tables and permutations for projected, shuffled, random-access training reads. diff --git a/docs/web/indexing/index.mdx b/docs/web/indexing/index.mdx index 9224ad50d..b40fb7918 100644 --- a/docs/web/indexing/index.mdx +++ b/docs/web/indexing/index.mdx @@ -1,169 +1,39 @@ --- title: "Indexing Data" sidebarTitle: "Overview" -description: "Optimize search performance in LanceDB using vector indexes, full-text search, and scalar indexes. Understand IVF-PQ indexing for efficient vector similarity search." +description: "Optimize search performance with LanceDB using vector indexes, full-text search, scalar indexes, and more." icon: "list" --- -An **index** is a data structure that facilitates efficient scans and lookups on the embeddings of a given dataset. LanceDB provides a comprehensive suite of indexes to optimize query performance across diverse workloads: +An **index** is a data structure that facilitates efficient scans and lookups on an embedded dataset. +LanceDB provides a comprehensive suite of indexes to optimize performance across different use cases and data types: -- **Vector Index**: Optimized for searching high-dimensional data (like images, audio, or text embeddings) by efficiently finding the most similar vectors +- **Vector Index**: Efficiently searches for similar vectors across high-dimensional data (e.g. images, audio, or text embeddings) - **Full-Text Search Index**: Enables fast keyword-based searches by indexing words and phrases -- **Scalar Index**: Accelerates filtering and sorting of structured numeric or categorical data (e.g., timestamps, prices) +- **Scalar Index**: Accelerates filtering and sorting of structured numeric or categorical data - -Scalar indices serve as a foundational optimization layer, accelerating filtering across diverse search workloads. They can be combined with: - -- Vector search (prefilter or post-filter results using metadata) -- Full-text search (combining keyword matching with structured filters) -- SQL scans (optimizing WHERE clauses on scalar columns) -- Key-value lookups (enabling rapid primary key-based retrievals) - - - -In SQL, see [`CREATE INDEX` and `DROP INDEX`](/sql/ddl#indexes) -- one column, server-chosen name. - - -## Supported Index Types {#supported-index-types} - -LanceDB provides a comprehensive suite of indexing strategies for different data types and use cases: +## Supported Indexes | Index | Use Case | Description | | :--------- | :------- | :---------- | -| `IVF` (Vector) | Large-scale vector search with configurable accuracy/speed trade-offs. Supports binary vectors with hamming distance. | Inverted File Index—a partition-based approximate nearest neighbor algorithm that groups similar vectors into partitions for efficient search.
Distance metrics: `l2` `cosine` `dot` `hamming`
Quantizations: `None/Flat` `PQ` `SQ` `RQ`| -| `IVF_HNSW` (Vector) | Large-scale vector search requiring both high recall and efficient partitioning. Combines the scalability of IVF with the search quality of HNSW. | Hybrid index combining IVF partitioning with HNSW graphs built within each partition. Provides improved search quality over pure IVF while maintaining scalability.
Distance metrics: `l2` `cosine` `dot`
Quantizations: `None/Flat` `SQ` `PQ`| +| `IVF` (Vector) | Large-scale vector search with configurable accuracy/speed trade-offs. | Inverted File Index—a partition-based approximate nearest neighbor algorithm that groups similar vectors into partitions for efficient search.
**Quantizations**: `None/Flat` `PQ` `SQ` `RQ`| +| `IVF_HNSW` (Vector) | Large-scale vector search requiring both high recall and efficient partitioning. Combines the scalability of IVF with the search quality of HNSW. | Hybrid index combining IVF partitioning with HNSW graphs in each partition. Provides improved search quality over pure IVF while maintaining scalability.
**Quantizations**: `None/Flat` `SQ` `PQ`| | `FTS` (Full-text search) | String columns (e.g., title, description, content) requiring keyword-based search with BM25 ranking. | Full-text search index using BM25 ranking algorithm. Tokenizes text with configurable tokenization, stemming, stop word removal, and language-specific processing. | | `BTree` (Scalar) | Numeric, temporal, and string columns with mostly distinct values. Best for selective equality, inequality, and range predicates. | Sorted index storing sorted copies of scalar columns with block headers in a btree cache. Header entries map to blocks of rows (4096 rows per block) for efficient disk reads. | | `Bitmap` (Scalar) | Low-cardinality columns with few thousand or fewer distinct values. Accelerates equality and range filters. | Stores a bitmap for each distinct value in the column, with one bit per row indicating presence. Memory-efficient for low-cardinality data. | | `LabelList` (Scalar) | List columns (e.g., tags, categories, keywords) requiring `array_contains_all` or `array_contains_any` filters. | Scalar index for `List` and `LargeList` columns of primitive values, using an underlying bitmap index structure to enable fast array membership lookups. | | `FM` (Scalar) | String or binary columns that need raw substring search. | FM-Index over `Utf8`, `LargeUtf8`, `Binary`, or `LargeBinary` data for filters such as `contains(path, 'needle')`. Use FTS instead for tokenized word search and BM25 ranking. | - -TypeScript currently doesn't support `IvfSq` (IVF with Scalar Quantization). - - - -**Operational checks** - -For vector indexes, use the same distance metric when creating the index and searching it. After appends or other writes, use `optimize()` to fold new rows into existing indexes, then check `index_stats(...)` or `wait_for_index(...)` if you need to confirm the index has caught up. `wait_for_index(...)` waits until the named indexes exist and report `num_unindexed_rows == 0`; it can time out if writes keep adding unindexed rows. - -By default, automatic vector indexing creates `IVF_PQ`, and scalar index creation defaults to -`BTree` unless you pass another scalar index config. `BTree` and `Bitmap` indexes target scalar -columns, not list columns; use `LabelList` for list containment filters. - - -### Quantization Types {#quantization-types} - -Vector indexes can use different quantization methods to compress vectors and improve search performance: +## Quantization +LanceDB also supports several [quantization](/indexing/vector-index) methods, used by vector indexes to compress vectors and reduce storage requirements: | Quantization | Use Case | Description | | :----------- | :------- | :---------- | | `PQ` (Product Quantization) | Default choice for most vector search scenarios. Use when you need to balance index size and recall. | Divides vectors into subvectors and quantizes each subvector independently. Provides a good balance between compression ratio and search accuracy. | -| `SQ` (Scalar Quantization) | Use when you need faster indexing or when vector dimensions have consistent value ranges. | Quantizes each dimension independently. Simpler than PQ but typically provides less compression. | | `RQ` (RabitQ Quantization) | Use when you need maximum compression or have specific per-dimension requirements. | Per-dimension quantization using a RabitQ codebook. Provides fine-grained control over compression per dimension. For `IVF_RQ`, vector dimensions must be divisible by `8`. | +| `SQ` (Scalar Quantization) | Use when you need faster indexing or when vector dimensions have consistent value ranges. | Quantizes each dimension independently. Simpler than PQ but typically provides less compression. | | `None/Flat` | Use for binary vectors (with `hamming` distance) or when you need maximum recall and have sufficient storage. | No quantization—stores raw vectors. Provides the highest accuracy but requires more storage and memory. | -## Understanding the IVF-PQ Index {#understanding-the-ivf-pq-index} - -An ANN (Approximate Nearest Neighbors) index is a data structure that quickly produces an approximate solution to the **k-nearest neighbors (kNN)** problem. -It greatly improves upon the runtime of a brute-force kNN search, while admitting a slight decrease in accuracy. LanceDB uses the disk-based indexing technique IVF-PQ, discussed below. - -LanceDB differs from other vector databases in that it is built on top of [Lance](https://github.com/lancedb/lance), an open-source columnar data format designed for performant ML workloads and fast random access. Due to the design of Lance, LanceDB's indexing philosophy adopts a primarily *disk-based* indexing philosophy. - -## IVF-PQ {#ivf-pq} - -LanceDB uses **IVF-PQ** indexing, which combines the clustering-based **Inverted File Index (IVF)** with **Product Quantization (PQ)** to efficiently compress embeddings. -The implementation provides several parameters to fine-tune the index's size, query throughput, latency, and recall. - -### Product Quantization {#product-quantization} - -Quantization is a compression technique used to reduce the dimensionality of an embedding to speed up search. - -Product quantization (PQ) works by dividing a large, high-dimensional vector of size into equally sized subvectors. Each subvector is assigned a "reproduction value" that maps to the nearest centroid of points for that subvector. The reproduction values are then assigned to a codebook using unique IDs, which can be used to reconstruct the original vector. - -![](/static/assets/images/indexing/ivfpq_pq_desc.png) - -It's important to remember that quantization is a *lossy process*, i.e., the reconstructed vector is not identical to the original vector. This results in a trade-off between the size of the index and the accuracy of the search results. - -As an example, consider starting with 128-dimensional vector consisting of 32-bit floats. Quantizing it to an 8-bit integer vector with 4 dimensions as in the image above, we can significantly reduce memory requirements. - - -Original: `128 × 32 = 4096` bits -Quantized: `4 × 8 = 32` bits - -Quantization results in a **128x** reduction in memory requirements for each vector in the index, which is substantial. - - -### Inverted File Index (IVF) Implementation {#inverted-file-index-ivf-implementation} - -While PQ helps with reducing the size of the index, IVF primarily addresses search performance. The primary purpose of an inverted file index is to facilitate rapid and effective nearest neighbor search by narrowing down the search space. - -In IVF, the PQ vector space is divided into *Voronoi cells*, which are essentially partitions that consist of all the points in the space that are within a threshold distance of the given region's seed point. These seed points are initialized by running K-means over the stored vectors. The centroids of K-means turn into the seed points which then each define a region. These regions are then are used to create an inverted index that correlates each centroid with a list of vectors in the space, allowing a search to be restricted to just a subset of vectors in the index. - -![](/static/assets/images/indexing/ivfpq_ivf_desc.webp) - -During query time, depending on where the query lands in vector space, it may be close to the border of multiple Voronoi cells, which could make the top-k results ambiguous and span across multiple cells. To address this, the IVF-PQ introduces the `nprobe` parameter, which controls the number of Voronoi cells to search during a query. The higher the `nprobe`, the more accurate the results, but the slower the query. -![](/static/assets/images/indexing/ivfpq_query_vector.webp) - -## HNSW Index Implementation {#hnsw-index-implementation} - -Approximate Nearest Neighbor (ANN) search is a method for finding data points near a given point in a dataset, though not always the exact nearest one. HNSW is one of the most accurate and fastest Approximate Nearest Neighbour search algorithms, It's beneficial in high-dimensional spaces where finding the same nearest neighbor would be too slow and costly. - -### Types of ANN Search Algorithms {#types-of-ann-search-algorithms} - -Approximate Nearest Neighbor (ANN) search is a method for finding data points near a given point in a dataset, though not always the exact nearest one. -For example, HNSW is an ANN index that performs well in high-dimensional spaces where other techniques prove too slow and costly. - -There are three main types of ANN search algorithms: - -* **Tree-based search algorithms**: Use a tree structure to organize and store data points. -* **Hash-based search algorithms**: Use a specialized geometric hash table to store and manage data points. These algorithms typically focus on theoretical guarantees, and don't usually perform as well as the other approaches in practice. -* **Graph-based search algorithms**: Use a graph structure to store data points, which can be a bit complex. - -HNSW is a graph-based algorithm. All graph-based search algorithms rely on the idea of a k-nearest neighbor (or k-approximate nearest neighbor) graph, which we outline below. -HNSW also combines this with the ideas behind a classic 1-dimensional search data structure: the skip list. - -### Understanding k-Nearest Neighbor Graphs {#understanding-k-nearest-neighbor-graphs} - -The k-nearest neighbor graph actually predates its use for ANN search. Its construction is quite simple: - -* Each vector in the dataset is given an associated vertex. -* Each vertex has outgoing edges to its k nearest neighbors. That is, the k closest other vertices by Euclidean distance between the two corresponding vectors. This can be thought of as a "friend list" for the vertex. -* For some applications (including nearest-neighbor search), the incoming edges are also added. - -Eventually, it was realized that the following greedy search method over such a graph typically results in good approximate nearest neighbors: - -* Given a query vector, start at some fixed "entry point" vertex (e.g. the approximate center node). -* Look at that vertex's neighbors. If any of them are closer to the query vector than the current vertex, then move to that vertex. -* Repeat until a local optimum is found. - -The above algorithm also generalizes to e.g. top 10 approximate nearest neighbors. - -Computing a k-nearest neighbor graph is actually quite slow, taking quadratic time in the dataset size. It was quickly realized that near-identical performance can be achieved using a k-approximate nearest neighbor graph. That is, instead of obtaining the k-nearest neighbors for each vertex, an approximate nearest neighbor search data structure is used to build much faster. -In fact, another data structure is not needed: This can be done "incrementally". -That is, if you start with a k-ANN graph for n-1 vertices, you can extend it to a k-ANN graph for n vertices as well by using the graph to obtain the k-ANN for the new vertex. - -One downside of k-NN and k-ANN graphs alone is that one must typically build them with a large value of k to get decent results, resulting in a large index. - -### Hierarchical Navigable Small Worlds (HNSW) {#hierarchical-navigable-small-worlds-hnsw} - -HNSW builds on k-ANN in two main ways: - -* Instead of getting the k-approximate nearest neighbors for a large value of k, it sparsifies the k-ANN graph using a carefully chosen "edge pruning" heuristic, allowing for the number of edges per vertex to be limited to a relatively small constant. -* The "entry point" vertex is chosen dynamically using a recursively constructed data structure on a subset of the data, similarly to a skip list. - -This recursive structure can be thought of as separating into layers: - -* At the bottom-most layer, a k-ANN graph on the whole dataset is present. -* At the second layer, a k-ANN graph on a fraction of the dataset (e.g. 10%) is present. -* At the Lth layer, a k-ANN graph is present. It is over a (constant) fraction (e.g. 10%) of the vectors/vertices present in the L-1th layer. - -Then the greedy search routine operates as follows: - -* At the top layer (using an arbitrary vertex as an entry point), use the greedy local search routine on the k-ANN graph to get an approximate nearest neighbor at that layer. -* Using the approximate nearest neighbor found in the previous layer as an entry point, find an approximate nearest neighbor in the next layer with the same method. -* Repeat until the bottom-most layer is reached. Then use the entry point to find multiple nearest neighbors (e.g. top 10). - ## Performance {#performance} #### Vector indexes {#vector-indexes} @@ -177,7 +47,7 @@ If vector search latency climbs with table size (i.e., queries that ran in milli | `IVF_HNSW_SQ` | Best recall/latency for unfiltered search; higher latency variance under selective filters. | | `IVF_FLAT` | Required for binary vectors with `hamming`. | -The distance metric is fixed once the index is built. Pick the distance metric based on how the embedding model was trained: `cosine` (unnormalized), `dot` (already-normalized, best performance), `l2` (general-purpose, default), `hamming` (binary). For parameter tuning, see [Vector Indexing](/indexing/vector-index). +The distance metric is fixed once the index is built. Pick the distance metric based on how the embedding model was trained: `cosine` (unnormalized), `dot` (already-normalized, best performance), `l2` (general-purpose, default), `hamming` (binary). If a query explicitly requests a different metric, the index cannot be used and the query falls back to a brute-force scan; LanceDB Enterprise may reject that scan on a large table. For parameter tuning, see [Vector Indexing](/indexing/vector-index). #### Scalar indexes {#scalar-indexes} diff --git a/docs/web/indexing/scalar-index.mdx b/docs/web/indexing/scalar-index.mdx index 68bffdda5..e8dcf6bb7 100644 --- a/docs/web/indexing/scalar-index.mdx +++ b/docs/web/indexing/scalar-index.mdx @@ -4,6 +4,7 @@ sidebarTitle: "Scalar Index" description: "Learn how to use scalar indexes in LanceDB for efficient metadata filtering and query optimization." icon: "tree" --- + import { PyScalarIndexBuild as ScalarIndexBuild, PyScalarIndexWait as ScalarIndexWait, @@ -27,7 +28,16 @@ LanceDB supports four types of scalar indexes: - `LABEL_LIST`: Special index for `List` and `LargeList` columns of primitive values supporting `array_contains_all` and `array_contains_any` queries. - `FM`: FM-Index over string or binary columns that accelerates substring search via `contains(col, 'needle')`. -## Choosing the Right Index Type {#choosing-the-right-index-type} + +Scalar indices serve as a foundational optimization layer, accelerating filtering across diverse search workloads. They can be combined with: + +- Vector search (prefilter results using metadata) +- Full-text search (combining keyword matching with structured filters) +- SQL scans (optimizing WHERE clauses on scalar columns) +- Key-value lookups (enabling rapid primary key-based retrievals) + + +## Choosing the Right Index Type | Data Type | Filter | Index Type | |:----------------------------------------------------------------|:------------------------------------------|:-------------| @@ -36,9 +46,9 @@ LanceDB supports four types of scalar indexes: | List of low cardinality of numbers or strings | `array_has_any`, `array_has_all` | `LABEL_LIST` | | String or binary (`Utf8`, `LargeUtf8`, `Binary`, `LargeBinary`) | `contains(col, 'needle')` | `FM` | -## Scalar Index Operations {#scalar-index-operations} +## Scalar Index Operations -### 1\. Build the Index {#1-build-the-index} +### 1. Build the Index You can create multiple scalar indexes within a table. By default, the index will be `BTREE`, but you can always configure another type like `BITMAP` @@ -52,7 +62,7 @@ You can create multiple scalar indexes within a table. By default, the index wil If you are using LanceDB Enterprise, the `create_scalar_index` API returns immediately, but the building of the scalar index is asynchronous. To wait until all data is fully indexed, you can specify the `wait_timeout` parameter on `create_scalar_index()` or call `wait_for_index()` on the table. -### 2\. Check Index Status {#2-check-index-status} +### 2. Check Index Status @@ -62,7 +72,7 @@ If you are using LanceDB Enterprise, the `create_scalar_index` API returns immed `wait_for_index(...)` waits until the named scalar indexes exist and `index_stats(...)` reports `num_unindexed_rows == 0`. If a table is receiving steady writes, that fully indexed state may not stabilize before the timeout. -### 3\. Update the Index {#3-update-the-index} +### 3. Update the Index Updating the table data (adding, deleting, or modifying records) requires that you also update the scalar index. This can be done by calling `optimize`, which will trigger an update to the existing scalar index. @@ -76,7 +86,7 @@ Updating the table data (adding, deleting, or modifying records) requires that y New data added after creating the scalar index will still appear in search results if optimize is not used, but with increased latency due to a flat search on the unindexed portion. LanceDB Enterprise automates the optimize process, minimizing the impact on search speed. -### 4\. Run Indexed Searches {#4-run-indexed-searches} +### 4. Run Indexed Searches The following scan will be faster if the column `book_id` has a scalar index: @@ -94,7 +104,7 @@ Scalar indexes can also speed up scans containing a vector search or full text s -## Indexing nested fields {#indexing-nested-fields} +## Indexing nested fields Scalar indexes can target a scalar field inside a struct by passing its full dotted path. The path is preserved end to end: it's the value you pass to `create_scalar_index`, it's what `list_indices()` reports under `columns`, and it's the column reference you use in filter predicates. @@ -110,7 +120,7 @@ table.search().where("metadata.user_id = 42").limit(1).to_list() Nested paths follow Lance field-path semantics: dot-separate each struct field from root to leaf (for example, `metadata.author.name`). The same convention applies to FTS and vector indexes. -## FM-Index for substring search {#fm-index-for-substring-search} +## FM-Index for substring search The `FM` index is a scalar index built over string or binary columns that accelerates substring lookups expressed as `contains(col, 'needle')`. Unlike the @@ -129,7 +139,7 @@ Use the FM-Index when: Pick `FTS` instead when you need word-level relevance ranking, phrase queries, or language-aware tokenization. -### Create an FM-Index {#create-an-fm-index} +### Create an FM-Index Build an FM-Index with the async `create_index` API by passing the `Fm` config in Python or `Index.fm()` in TypeScript. In Rust, use `Index::Fm(FmIndexBuilder::default())`. @@ -166,7 +176,7 @@ table.search().where("contains(text, 'needle')").limit(10).to_pandas() `list_indices()` reports the index type as `"Fm"`. -## Index UUID Columns {#index-uuid-columns} +## Index UUID Columns LanceDB supports scalar indexes on UUID columns (stored as `FixedSizeBinary(16)`), enabling efficient lookups and filtering on UUID-based primary keys. @@ -177,7 +187,7 @@ LanceDB supports scalar indexes on UUID columns (stored as `FixedSizeBinary(16)` - TypeScript SDK version `0.19.0` or later -### 1\. Define UUID Type {#1-define-uuid-type} +### 1. Define UUID Type @@ -185,7 +195,7 @@ LanceDB supports scalar indexes on UUID columns (stored as `FixedSizeBinary(16)` -### 2\. Generate UUID Data {#2-generate-uuid-data} +### 2. Generate UUID Data @@ -193,7 +203,7 @@ LanceDB supports scalar indexes on UUID columns (stored as `FixedSizeBinary(16)` -### 3\. Create Table with UUID Column {#3-create-table-with-uuid-column} +### 3. Create Table with UUID Column @@ -201,7 +211,7 @@ LanceDB supports scalar indexes on UUID columns (stored as `FixedSizeBinary(16)` -### 4\. Create and Wait for the Index {#4-create-and-wait-for-the-index} +### 4. Create and Wait for the Index @@ -209,7 +219,7 @@ LanceDB supports scalar indexes on UUID columns (stored as `FixedSizeBinary(16)` -### 5\. Perform Operations with the UUID Index {#5-perform-operations-with-the-uuid-index} +### 5. Perform Operations with the UUID Index @@ -217,7 +227,7 @@ LanceDB supports scalar indexes on UUID columns (stored as `FixedSizeBinary(16)` -## Index nested fields {#index-nested-fields} +## Index nested fields You can build a scalar index on a field inside a struct column by passing the canonical dot-separated path to `create_index`. This is useful when filters diff --git a/docs/web/indexing/vector-index.mdx b/docs/web/indexing/vector-index.mdx index b623311a5..24ad2a2af 100644 --- a/docs/web/indexing/vector-index.mdx +++ b/docs/web/indexing/vector-index.mdx @@ -1,7 +1,7 @@ --- title: "Vector Indexes" sidebarTitle: "Vector Index" -description: "Build and optimize LanceDB vector indexes, including IVF, HNSW and binary quantized indexes." +description: "Build and manage LanceDB vector indexes." icon: "arrow-up-right-dots" --- @@ -23,216 +23,156 @@ import { PyVectorIndexDistanceRange as VectorIndexDistanceRange, PyVectorIndexBypassRecall as VectorIndexBypassRecall, PyVectorIndexCustomName as VectorIndexCustomName, + PyQuantizationCustomParams as QuantizationCustomParams, } from '/snippets/indexing.mdx'; -You can create and manage multiple vector indexes on any Lance dataset. LanceDB offers two kinds of vector indexing algorithms: **Inverted File (IVF)** and **Hierarchical Navigable Small World (HNSW)**. +Vector indexes are robust tools in facilitating fast searches across large numeric datasets. +LanceDB implements **ANN (Approximate Nearest-Neighbor)** queries with several techniques that provide benefits across a variety of use cases. +## Choosing the Right Index + +LanceDB vector indexes are combined with several [quantization](/indexing/vector-index) techniques to admit efficient storage. +The following table lists provided quantized vector indexes and their common use cases. You can specify index type manually in +Lance with `index_type`. + + +| If your priority is... | Use this index | Why | Approx. compression ratio | Python config class | +| :--- | :--- | :--- | :--- | :--- | +| Maximum compression | `IVF_RQ` | IVF indexing with RaBitQ quantization | Around `1/32` of raw size | `IvfRq` | +| Higher accuracy at small dimensions (`dimension <= 256`) | `IVF_PQ` | IVF indexing with product quantization | Usually `1/64` to `1/16` of raw size (depends on `num_sub_vectors`) | `IvfPq` | +| Best recall/latency trade-off | `IVF_HNSW_SQ` | IVF-HNSW indexing with scalar | Typically a little larger than `1/4` of raw size | `IvfHnswSq` | +| Highest recall / no quantization | `IVF_HNSW_FLAT` | IVF-HNSW indexing with no quantization | Around raw vector size plus HNSW graph overhead | `IvfHnswFlat` | + + +If your vector search frequently includes metadata filters (`where(...)`), use `IVF_RQ` or `IVF_PQ`. In filtered workloads, HNSW-backed IVF indexes such as `IVF_HNSW_FLAT` and `IVF_HNSW_SQ` can show higher latency variance. + + +## Understanding Vector Indexes + +LanceDB offers two vector indexes, which can be created on any numeric Lance dataset: +**Inverted File (IVF)** and **Hierarchical Navigable Small World (HNSW)**. + +### IVF + +The **Inverted File Index (IVF)** accelerates ANN searches by drastically reducing the search space. The index consists of +a small set of *centroids* corresponding to an approximate solution to the +[$k$-means clustering](https://en.wikipedia.org/wiki/K-means_clustering) problem. +Each vector remembers its nearest centroid, and each centroid remembers its associated set of vectors, +called its *partition*. + + IVF vector-space partitioning + + +At query time, we can compare the queried vector to the smaller set of *centroids* (as opposed to the entire dataset) +for a closest match, then run a brute-force comparison against its resulting partition. This technique quickly prunes a large search space, +giving an approximate ANN result. + +However, observe that a queried vector may lie near the boundary of $2$ or more partitions; thus, the true nearest neighbors are scattered across several different partitions. + To address this, LanceDB exposes the `nprobes` parameter, which specifies the number of partitions searched. +A high `nprobes` parameter will yield more accurate results at slightly higher runtime. + + + IVF vector-space partitioning + + +### HNSW +**Hierarchical Navigable Small World (HNSW)** constructs a layered graph hierarchy on the vector set, with edges representing distances. +We can visualize an HNSW index as a vertical stack of graphs, with the top layer having very few edges and +each other layer having a multiplicative factor more edges than the layer above it. + +High layers of a HNSW hierarchy represent sparse, higher-distance networks, and lower layers represent finer, lower-distance networks. +To query a vector $q$, the index proceeds iteratively through layers, first finding $q$'s nearest neighbor in the graph, then proceeding recursively +through the induced subhierarchy until the lowest layer is reached. + + + HNSW layered graph hierarchy + + +To visualize this process, imagine that you must drive your car from San Francisco to a specific house in Boston. Initially, you must first drive thousands of miles +on the interstate freeway I-90 E. Eventually, you merge onto the Massachusetts Turnpike, the center +of the greater Boston highway system. From there, you use a series of increasingly smaller, narrower roads within the city (Charles River Bridge, St. Paul St, +Thatcher St) before finally reaching the house. + +A key observation is that you must initially travel far distances through long-distance road networks +(the interstate freeway system), before proceeding to finer and finer road networks (greater Boston highway system, central Brookline neighborhood connectors) before finally reaching +your destination. This iterative series of road networks mimics the layered graph traversals performed by a HNSW query. **IVF + HNSW** -In LanceDB, HNSW is not exposed as a top-level vector index. Instead, it's available as a sub-index inside IVF partitions. What this means in practice is that vectors are first partitioned by IVF, then each selected partition is searched using an HNSW graph. LanceDB supports the unquantized variant `IVF_HNSW_FLAT`, along with quantized variants such as `IVF_HNSW_PQ` and `IVF_HNSW_SQ`. This combines IVF's scalability with HNSW's higher-recall ANN search within partitions. +In LanceDB, HNSW is not exposed as a top-level vector index. Instead, it's available as a substructure which +further indexes the selected vectors inside each IVF partition. +This combines the scalability of IVF with the high recall of HNSW. +LanceDB supports IVF-HNSW-based quantized indexes `IVF_HNSW_FLAT`, `IVF_HNSW_PQ`, and `IVF_HNSW_SQ`. -### Manual Indexing {#manual-indexing} -If using LanceDB OSS, you will have to create the vector index manually, by calling `table.create_index()`, and updating the index as new data arrives and tuning its parameters is also a manual process. +## Using Vector Indexes +Learn how to configure, build, and search LanceDB vector indexes, including build and search time parameters, asynchronous objects, and several examples. -### Automatic Indexing {#automatic-indexing} +### Configuration - Enterprise-only -Vector indexing is managed **automatically** in LanceDB Enterprise. As soon as data is updated, the system updates the index and optimizates it. *This is done asynchronously as a background process*. - -When you create a table in LanceDB Enterprise, LanceDB automatically: - -- Infers the vector columns from the schema -- Create an optimized `IVF_PQ` index without manual configuration -- Automatically configure indexing parameters - -The default distance is `l2` (Euclidean). - - -You can call `create_index()` with different parameters to create a new index -- this replaces any existing index. -Although the `create_index` API returns immediately, the building of the vector index is asynchronous. To wait until all data is fully indexed, you can specify the `wait_timeout` parameter. - - -Use the same distance metric for index creation and search. Once a vector index exists, queries use the metric stored with that index. If you need to confirm an async build or refresh is finished, `wait_for_index(...)` waits for the named index to exist and for `index_stats(...)` to report `num_unindexed_rows == 0`; it can time out if new writes keep arriving. - -Rows appended after an index build remain outside that index until optimization refreshes it. Normal -search still checks those unindexed rows with a slower fallback path; `fast_search()` skips that -fallback and searches only indexed rows. - -## Choose the Right Index {#choose-the-right-index} - -Use this table as a quick starting point for choosing the right index type and quantization method for your use case: - -| If your top priority is... | Use this index | Why | Typical compressed size vs. raw vectors | -| :--- | :--- | :--- | :--- | -| Highest recall / no quantization | `IVF_HNSW_FLAT` | Uses raw vectors inside the IVF+HNSW structure, avoiding quantization loss. | Around raw vector size plus HNSW graph overhead | -| Best recall/latency trade-off | `IVF_HNSW_SQ` | Combines IVF partitioning with HNSW graph search for strong quality at low latency. | Typically a little larger than `1/4` of raw size | -| Maximum compression | `IVF_RQ` | RaBitQ-style quantization with very strong compression. | Around `1/32` of raw size | -| Higher accuracy at small dimensions (`dimension <= 256`) | `IVF_PQ` | On small-dimensional vectors, `IVF_PQ` often provides higher accuracy with similar performance compared to `IVF_RQ`. | Usually `1/64` to `1/16` of raw size (depends on `num_sub_vectors`) | - - -If your vector search frequently includes metadata filters (`where(...)`), prefer `IVF_RQ` or `IVF_PQ`. In filtered workloads, HNSW-backed IVF indexes such as `IVF_HNSW_FLAT` and `IVF_HNSW_SQ` can show higher latency variance. - - -Compression ratios are practical rules of thumb and can vary with vector distribution, metric, and configuration. -For small dimensions, choose `IVF_PQ` for accuracy, not for guaranteed higher compression than `IVF_RQ`. - -### Index Tuning {#index-tuning} - -Start with these values, then tune for your workload: - -- HNSW-backed IVF indexes (`IVF_HNSW_FLAT`, `IVF_HNSW_SQ`, `IVF_HNSW_PQ`) - - `num_partitions`: start at `num_rows // 1,048,576` (rounded to an integer) - - Lower `num_partitions` can reduce search latency, but index build may become slower because partitions are larger. - - `ef_construction`: start at `150`; increase for better recall, decrease for faster indexing. -- `IVF_RQ` - - `num_partitions`: start at `num_rows // 4096` (rounded to an integer). This is a strong default for most datasets. -- `IVF_PQ` - - `num_partitions`: start at `num_rows // 4096` (rounded to an integer). - - `num_sub_vectors`: start at `dimension // 8`. Increase for better recall, decrease for faster search and smaller indexes. - - For small dimensions (`dimension <= 256`), `IVF_PQ` is often preferred over `IVF_RQ` for better accuracy at similar query performance. - -## Example: Construct an IVF Index {#example-construct-an-ivf-index} - -In this example, we will create an index for a table containing 1536-dimensional vectors. The index will use IVF_PQ with L2 distance, which is well-suited for high-dimensional vector search. - -Make sure you have enough data in your table (at least a few thousand rows) for effective index training. - -### Index Configuration {#index-configuration} - -Sometimes you need to configure the index beyond default parameters: - -- Index Types: - - `IVF_HNSW_FLAT`: highest recall, with no vector quantization - - `IVF_HNSW_SQ`: best recall/latency trade-off - - `IVF_RQ`: best compression for large, high-dimensional datasets - - `IVF_PQ`: often higher accuracy than `IVF_RQ` for small dimensions (`<= 256`) at similar query performance -- `metrics`: default is `l2`, other available are `cosine` or `dot` - - When using `cosine` similarity, distances range from 0 (identical vectors) to 2 (maximally dissimilar) -- `num_partitions`: use index-specific starting points from the section above: - - HNSW-backed IVF indexes (`IVF_HNSW_FLAT`, `IVF_HNSW_SQ`, `IVF_HNSW_PQ`): `num_rows // 1,048,576` - - `IVF_RQ` and `IVF_PQ`: `num_rows // 4096` -- `target_partition_size`: alternative IVF sizing knob that asks LanceDB to derive the partition - count from a target number of rows per partition. If you set both `num_partitions` and - `target_partition_size`, `num_partitions` takes precedence. -- `num_sub_vectors`: applies to `IVF_PQ`; start with `dimension // 8`. Larger values often improve recall but can slow search. - -Let's take a look at a sample request for an IVF index: - - - - - {VectorIndexConfigureIvf} - - - -### 1\. Setup {#1-setup} - -Connect to LanceDB and open the table you want to index. - - - - {VectorIndexSetup} - - - -### 2\. Construct an IVF Index {#2-construct-an-ivf-index} - -Create an `IVF_PQ` index with `cosine` similarity. Specify `vector_column_name` if you use multiple vector columns or non-default names. For a vector field nested inside a struct, use dot notation (e.g. `image.embedding`); see [Selecting the vector column](/search/vector-search#selecting-the-vector-column) for the full syntax. You can switch `index_type` to `IVF_RQ`, `IVF_HNSW_SQ`, or `IVF_HNSW_FLAT` depending on your recall/latency/compression target. - - - - {VectorIndexBuildIvf} - - - -#### Indexing nested vector fields {#indexing-nested-vector-fields} - -If your vector column lives inside a struct, pass its full dotted path as `vector_column_name`. The same path is used at query time and is what `list_indices()` reports under `columns`: - - - - {VectorIndexNestedField} - - - - -Nested paths follow Lance field-path semantics: dot-separate each struct field from root to leaf (for example, `image.thumbnail.embedding`). The same convention applies to FTS and scalar indexes. - - -### Async API and Config Objects {#async-api-and-config-objects} - -With asynchronous Python connections, create vector indexes with `await table.create_index("vector", config=...)`. The `config` object carries the same index choices you configure in the synchronous API, such as distance metric, partition count, and quantization settings: - - - - {VectorIndexAsyncConfig} - - - -Use these Python config classes for the index types shown on this page: - -| Index type | Python config class | -| :--- | :--- | -| `IVF_FLAT` | `IvfFlat` | -| `IVF_PQ` | `IvfPq` | -| `IVF_RQ` | `IvfRq` | -| `IVF_SQ` | `IvfSq` | -| `IVF_HNSW_FLAT` | `IvfHnswFlat` | -| `IVF_HNSW_PQ` | `IvfHnswPq` | -| `IVF_HNSW_SQ` | `IvfHnswSq` | - -### 3\. Query the IVF Index {#3-query-the-ivf-index} - -Search using a random 1,536-dimensional embedding. - - - - {VectorIndexQueryIvf} - - - -#### Search Configuration {#search-configuration} - -Core knobs available on a vector search call: +#### Build-time Parameters | Parameter | Description | | :--- | :--- | -| `limit` | Number of results to return (`k`). | -| `nprobes` | Shorthand that sets both `minimum_nprobes` and `maximum_nprobes` to the same value. LanceDB auto-tunes this by default. | -| `minimum_nprobes` | Partitions that are *always* scanned. Higher values raise recall at the cost of latency. | -| `maximum_nprobes` | Upper bound on partitions scanned. The partitions above `minimum_nprobes` are only searched if the initial pass does not return enough results — useful for narrow filters. Set to `0` to remove the cap. | -| `ef` | HNSW search-time exploration factor. Relevant for `IVF_HNSW_FLAT` and `IVF_HNSW_SQ`; start around `1.5 * k` and increase up to `10 * k` for higher recall. | -| `refine_factor` | Reads additional candidates and reranks them in memory to recover recall lost to quantization. | +| `distance_type` | Default is `l2`, others available are `cosine` and `dot`. +| `num_partitions` | The number of IVF partitions constructed (corresponds to the $k$ in $k$-means clustering). This takes precedence over `target_partition_size` if both are set. | +| `target_partition_size` | An alternative IVF sizing knob that derives the partition count by setting the number of rows per partition. `num_partitions` takes precedence over `target_partition_size` if both are set. If neither is set the number of partitions is automatically calculated based on the number of rows and the index type. | +| `num_sub_vectors` | Applies to `IVF_PQ`; defaults to `dimension // 16` (or `dimension // 8` if not a multiple of 16). Larger values produce better recall and slower search. | +| `max_iterations` | Maximum number of k-means training iterations, for every IVF/HNSW index type. Default `50`. Increase for larger datasets or to improve training quality. | +| `sample_rate` | Number of k-means training samples per partition, for every IVF/HNSW index type. Default `256`. Higher values increase both accuracy and training time. | + +#### Search-time Parameters + +| Parameter | Description | +| :--- | :--- | +| `limit` | Number of results to return (the `k` in `k-ANN`). | +| `nprobes` | Shorthand that sets both `minimum_nprobes` and `maximum_nprobes` to the same value. LanceDB defaults this to 20 which is a good default for many cases. At very high scales you will likely need to experiment to find your preferred recall / latency balance. | +| `minimum_nprobes` | Minimum number of partitions scanned. | +| `maximum_nprobes` | Maximum number of partitions scanned. Only scans more than `minimum_nprobes` if an initial pass does not return enough results — useful for narrow filters. Set to `0` to remove the cap. | +| `ef` | HNSW search-time exploration factor. Start around `1.5 * k` and increase up to `10 * k` for higher recall. | +| `refine_factor` | Reads and reranks additional candidates in memory to recover recall lost to quantization. | +| `distance_range(lower_bound, upper_bound)` | Return only rows whose distance falls within `[lower_bound, upper_bound)`. Either bound is optional. Useful for near-duplicate detection or "close-enough" matching. | +| `bypass_vector_index()` | Ignore the ANN index entirely and perform an exact (flat) scan. Can be used to measure ANN `recall@k`, or to query with a metric the index was not built for (e.g., a non-cosine query on a multivector column). | -**Filtered queries and adaptive nprobes.** When a `where(...)` filter is active, LanceDB starts by scanning `minimum_nprobes` partitions and only extends toward `maximum_nprobes` if fewer than `limit` rows survive the filter. Setting `minimum_nprobes == maximum_nprobes` (or calling `nprobes(n)`) disables this adaptive behavior and fixes the partition count. +The `distance_type` can be specified at search time in addition to build time. If +you do this, set it to the same value used to build the vector index. If the search +metric does not match the index metric, LanceDB cannot use the index and falls +back to a costly flat search. On LanceDB Cloud, the brute-force KNN safety limit +can reject that search on a large table instead of executing it. LanceDB +Enterprise doesn't have the limit. + +When the search metric is omitted, current SDKs use the index metric if an index +is available. Some older SDK versions sent `l2` when it was omitted, so explicitly +set the matching metric or upgrade the SDK when querying a non-`l2` index with an +older client. +**Recommended `nprobes` behavior by index type:** + +| Index type | Guidance | +| :--- | :--- | +| `IVF_HNSW_FLAT`, `IVF_HNSW_SQ` | Keep the default `nprobes`, then tune `ef` first. Expect higher latency variance under filtered search. | +| `IVF_RQ`, `IVF_PQ` | Keep the default `nprobes` and raise when recall is insufficient. If using a selective filter you may need to increase `maximum_nprobes` if you do not received enough results. | + + + +**Filtered queries and adaptive `nprobes`.** When a `where(...)` filter is active, LanceDB initially scans `minimum_nprobes` +partitions and uses a wider scan if too few rows are found. +Set `minimum_nprobes == maximum_nprobes` or call `nprobes(n)` to instead fix the partition count. + + +Here is an example of a vector search exercising several of the above parameters. + {VectorIndexNprobes} -Recommended `nprobes` behavior by index type: -| Index type | Guidance | -| :--- | :--- | -| `IVF_HNSW_FLAT`, `IVF_HNSW_SQ` | Keep the auto-tuned `nprobes`, then tune `ef` first. Expect higher latency variance under filtered search. | -| `IVF_RQ` | Keep auto-tuned `nprobes`; raise only when recall is insufficient. | -| `IVF_PQ` | Keep auto-tuned `nprobes`; raise when recall is insufficient. Often preferred over `IVF_RQ` when `dimension <= 256`. | - -#### Advanced Search Controls {#advanced-search-controls} - -These controls are useful for thresholded retrieval, recall measurement, and working around index-level metric constraints. - -| Method | Description | -| :--- | :--- | -| `distance_range(lower_bound, upper_bound)` | Return only rows whose distance falls within `[lower_bound, upper_bound)`. Either bound is optional. Useful for near-duplicate detection or "close-enough" matching. | -| `bypass_vector_index()` | Skip the ANN index and perform an exhaustive (flat) scan. Primary uses: (1) compute ground-truth results to measure ANN recall@k, and (2) query with a metric the index was not built for (e.g., a non-cosine query on a multivector column). | +LanceDB also supports advanced search-time controls for thresholded retrieval, recall measurement, and working around index-level metric constraints. **Thresholding with `distance_range`:** @@ -242,9 +182,9 @@ These controls are useful for thresholded retrieval, recall measurement, and wor -**Measuring recall with `bypass_vector_index`:** +**Using `bypass_vector_index`:** -Compare ANN results against a flat-scan ground truth to compute recall@k. This is the standard way to pick `nprobes` for your workload. +Use `bypass_vector_index` to compute an exact **kNN** result. Note that exact queries may be prohibitively slow on production scales. @@ -252,105 +192,102 @@ Compare ANN results against a flat-scan ground truth to compute recall@k. This i - -Flat search is $O(n)$ — reserve `bypass_vector_index()` for sampled recall measurements or small tables, not production queries. - - -Multivector indexing currently requires `distance_type="cosine"` — `l2` is rejected at index-creation time. That restriction is why `bypass_vector_index()` is the escape hatch for non-cosine queries on a multivector column: the metric you want at query time cannot be served by the index, so you fall back to a flat scan. See [Multivector Search](/search/vector-search) for the full rules. +Multivector indexing currently requires `distance_type="cosine"`. Use `bypass_vector_index()` for non-`cosine` queries on a multivector column. See [Multivector Search](/search/vector-search) for the full rules. -## Example: Construct an HNSW Index {#example-construct-an-hnsw-index} +#### Async API and Config Objects -### Index Configuration {#index-configuration-2} - -There are four key parameters to set when constructing an HNSW index: - -- `index_type`: choose `IVF_HNSW_SQ` for a strong recall/latency/size trade-off, or `IVF_HNSW_FLAT` when you want the IVF+HNSW structure without vector quantization. -- `metric`: The default is `l2` euclidean distance metric. Other available are `dot` and `cosine`. -- `m`: The number of neighbors to select for each vector in the HNSW graph. -- `ef_construction`: The number of candidates to evaluate during the construction of the HNSW graph. - -### 1\. Construct an HNSW Index {#1-construct-an-hnsw-index} - -The snippet below uses `IVF_HNSW_SQ`. If you want the unquantized variant, change `index_type` to `IVF_HNSW_FLAT`. +Create vector indexes asynchronously with `await table.create_index("vector", config=...)`. The `config` object +admits the same build-time parameters described above — pass an instance of a Python config class from the table in [Choosing the Right Index](#choosing-the-right-index): - {VectorIndexBuildHnsw} + {VectorIndexAsyncConfig} -### 2\. Query the HNSW Index {#2-query-the-hnsw-index} +### IVF Indexes + +This example creates and queries an `IVF_PQ` index for a table of vectors with respect to `cosine` similarity. +Specify `vector_column_name` if you have multiple vector columns or non-default names. - {VectorIndexQueryHnsw} + {VectorIndexBuildIvf + VectorIndexQueryIvf} -## Example: Construct a Binary Vector Index {#example-construct-a-binary-vector-index} + +TypeScript currently doesn't support `IvfSq` (IVF with Scalar Quantization). + -Binary vectors are useful for hash-based retrieval, fingerprinting, or any scenario where data can be represented as bits. - -### Index Configuration {#index-configuration-3} - -- Store binary vectors as fixed-size binary data (uint8 arrays, with 8 bits per byte). For storage, pack binary vectors into bytes to save space. -- Index Type: `IVF_FLAT` is used for indexing binary vectors -- `metric`: the `hamming` distance is used for similarity search -- The dimension of binary vectors must be a multiple of 8. For example, a 128-dimensional vector is stored as a uint8 array of size 16. - - -**`IVF_FLAT` + `hamming` is the only supported path for binary vectors.** - -- `hamming` distance is only valid on packed binary (uint8) data; it is rejected on float vector columns. -- Quantized index types (`IVF_PQ`, `IVF_RQ`, `IVF_SQ`, `IVF_HNSW_PQ`, `IVF_HNSW_SQ`) do not accept binary inputs — their `distance_type` is restricted to `l2`, `cosine`, or `dot`. - - -### 1\. Create Table and Schema {#1-create-table-and-schema} +For a vector field nested inside a struct, pass its full dotted path as `vector_column_name` (e.g. `image.embedding`) — the same path is used at query time and is what `list_indices()` reports under `columns`. See [Selecting the vector column](/search/vector-search#selecting-the-vector-column) for the full path syntax. - {VectorIndexBinarySchema} + {VectorIndexNestedField} -### 2\. Generate and Add Data {#2-generate-and-add-data} +### IVF-HNSW Indexes + +Beyond the general build-time parameters above, two additional parameters are specific to IVF-HNSW indexes: + +| Parameter | Description | +| :--- | :--- | +| `m` | The number of neighbors to select for each vector in the HNSW graph. | +| `ef_construction` | The number of candidates to evaluate during the construction of the HNSW graph. Start at `150`; increase for better recall, decrease for faster indexing. | + +Partition sizing follows the general `num_partitions`/`target_partition_size` guidance above. +The snippet below builds and queries an `IVF_HNSW_SQ` index. - {VectorIndexBinaryAddData} + {VectorIndexBuildHnsw + VectorIndexQueryHnsw} -### 3\. Construct the Binary Index {#3-construct-the-binary-index} +### Managing Vector Indexes - - - {VectorIndexBinaryBuildIndex} - - + Enterprise-only +In LanceDB Enterprise, vector indexes are managed **automatically**. The system asynchronously updates and optimizes indexes as a background process: +- Automatically manages indexing parameters and storage +- Infers vector columns from the schema -### 4\. Vector Search {#4-vector-search} + Open-Source + LanceDB OSS users can manually create vector indexes by calling `table.create_index()`. + See the above sections for guidance on manually tuning index parameters as data changes. - - - {VectorIndexBinarySearch} - - + +`create_index()` returns immediately, but the vector index builds asynchronously. +To wait until all data is indexed, specify the `wait_timeout` parameter, or call `wait_for_index(...)` afterward — +it waits for the named index to exist and for `index_stats(...)` to report `num_unindexed_rows == 0`. + -## Check Index Status {#check-index-status} + +Rows appended after an initial index build remain outside the index until refreshed manually (OSS) or automatically (Enterprise). Normal +search still checks those unindexed rows with a slower fallback path; `fast_search()` skips that +fallback and searches only indexed rows. + -Vector index creation runs in the background and may take some time to complete. While it is ongoing, you can check its status either programmatically through the API or from the **LanceDB Enterprise UI**. + +**Operational checks** + +After appends or other writes, use `optimize()` to fold new rows into existing indexes. + +#### Check Index Status + +Vector index creation runs in the background and may take some time to complete. +While it is ongoing, you can check its status through the API or the **LanceDB Enterprise UI**. In the LanceDB Enterprise UI, navigate to your table page - the "Index" column reflects each column's index status: it is blank when no index exists, shows an "in progress" label while the index is being built, and shows the index type once the build completes. -Programmatically, use `list_indices()` and `index_stats()`. **By default**, the index name is formed by appending `_idx` to the column name (e.g., a `keywords_embeddings` column produces `keywords_embeddings_idx`). Note that `list_indices()` only returns information after the index is fully built. -To wait until all data is fully indexed, you can specify the `wait_timeout` parameter on `create_index()` or call `wait_for_index()` on the table. +To check status programmatically, use `list_indices()` and `index_stats()`. **By default**, the index name is formed by appending `_idx` to the column name (e.g., a `keywords_embeddings` column produces `keywords_embeddings_idx`). Note that `list_indices()` only returns information after the index is fully built. Each entry returned by `list_indices()` also carries detailed per-index metadata, so you can inspect an index without a follow-up `index_stats()` call. Node.js exposes the same fields in camelCase (`num_indexed_rows` → `numIndexedRows`): -| Field | What it tells you | +| Parameter | Description | | :--- | :--- | | `num_indexed_rows`, `num_unindexed_rows` | Index coverage over the table | | `size_bytes` | Total size of the index files on disk | @@ -359,9 +296,6 @@ Each entry returned by `list_indices()` also carries detailed per-index metadata | `index_uuid`, `type_url` | Internal identifiers for the index segment | | `index_details` | Type-specific details (e.g. IVF partition counts or quantization settings) | - -These fields are populated for local and embedded tables. On LanceDB Enterprise remote tables they are returned as `None` / `undefined` until the server response surfaces them. - @@ -369,9 +303,14 @@ These fields are populated for local and embedded tables. On LanceDB Enterprise -## Custom Index Names {#custom-index-names} -The `{column}_idx` suffix is a default convention, not the only supported naming path. Pass `name=...` to `create_index()` to override it — useful when you want to manage multiple indexes on the same column (for example, side-by-side `IVF_PQ` and `IVF_HNSW_SQ` builds) or when you script index replacement by name. Once set, `list_indices()`, `index_stats(name)`, and `wait_for_index([name])` all reference the custom name. + +These fields are populated for local and embedded tables. On LanceDB Enterprise remote tables they are returned as `None` / `undefined` until the server response surfaces them. + +#### Custom Index Names + +The `{column}_idx` suffix is the default naming convetion. +Pass `name=...` to `create_index()` to override it. Once set, the custom name will be reflected in `list_indices()`, `index_stats(name)`, and `wait_for_index([name])`. @@ -379,74 +318,78 @@ The `{column}_idx` suffix is a default convention, not the only supported naming -Quantization compresses high-dimensional float vectors into a smaller, approximate representation, where instead of storing every vector as a float32 or float64, it's stored in compressed form, without too much of a compromise in search quality. +## Quantization {#quantization} -Use quantization when: +**Quantization** is used in LanceDB to efficiently compress and store vector indexes. We discuss only the quantization techniques here; +discussion of LanceDB vector indexes and quantized vector indexes can be found [here](/indexing/vector-index). -- You have a large dataset with relatively high-dimensional vectors (512, 768, 1024+) -- Index build time and query latency matter +### Quantization Techniques +LanceDB provides $3$ distinct quantization techniques: Product Quantization (PQ), RaBitQ Quantization (RQ), and Scalar Quantization (SQ). +Recall that all quantizations perform **lossy** compression, in that they irreversibly lose some degree of precision in order to +compactly store an index. -LanceDB currently exposes multiple quantized vector index types, including: -- `IVF_PQ` -- Inverted File index with Product Quantization (default). See the [vector indexing guide](/indexing/vector-index) for `IVF_PQ` examples. -- `IVF_SQ` -- Inverted File index with Scalar Quantization. This is available in Python and Rust; TypeScript does not currently expose `IvfSq`. -- `IVF_RQ` -- Inverted File index with **RaBitQ** quantization (binary, 1 bit per dimension). Requires vector dimensions divisible by `8`. See [below](#rabitq-quantization) for details. -- `IVF_HNSW_SQ` -- IVF partitions with an **HNSW graph per partition** plus **Scalar Quantization**. Strong recall/latency/size trade-off for most workloads. -- `IVF_HNSW_PQ` -- IVF partitions with an **HNSW graph per partition** plus **Product Quantization**. Prefer when PQ-level compression matters and you still want HNSW-style in-partition search. +#### Product Quantization (PQ) +To visualize PQ, assume a vector dataset has $d$ dimensions, with a **chunk** of a vector denoting a contiguous block of entries. Imagine that each vector has + $m$ disjoint chunks of $d/m$ entries each, where the first chunk represents entries $0$ through $d-1$, the second contains entries $d$ through $2d - 1$, and so on. -Two axes are being combined here: whether partitions are searched flatly or via an HNSW graph (`IVF_*` vs. `IVF_HNSW_*`), and which quantizer compresses the vectors (`PQ`, `RQ`, or `SQ`). `IVF_PQ` is the default and works well in many cases. For more drastic compression, RaBitQ (`IVF_RQ`) is a reasonable option. For higher recall at low latency, the HNSW-backed variants are usually the right pick. The ["Choose the Right Index"](/indexing/vector-index#choose-the-right-index) table on the vector indexing page is the canonical decision tool. +Now, for each $i$, let $S_i$ represent the set containing chunk $i$ of each vector (entries $(i-1)d$ to $di - 1$). +For each $S_i$ independently, a small set of **centroids** is computed corresponding to an approximate solution to the $k$-means clustering problem. -Use the same distance metric when training the index and running queries against it. For IVF-based indexes, `num_partitions` controls the number of groups and `sample_rate` controls how many training vectors are sampled per partition, so the training sample is roughly `sample_rate * num_partitions`. +For each original vector in the dataset, every chunk is associated to its nearest centroid; thus, the vector itself is associated with the concatenation of $m$ centroids. +We then gather all our centroids (from all chunks) into a single lookup table, and for each vector, we store the concatenation of IDs of its corresponding centroids. +At query time, we need only to compare each chunk of the queried vector with our set of centroids. -## RaBitQ quantization {#rabitq-quantization} + + IVF vector-space partitioning + -RaBitQ is a binary quantization method that represents each normalized embedding using **1 bit per dimension**, plus a couple of small corrective scalars. In practice, a 1,024-dimensional `float32` vector that would normally take 4 KB can be compressed to roughly a few hundred bytes with RaBitQ, while still maintaining reasonable recall. +In the above example, the original vector is split into chunks (subvectors), each of which is associated to a centroid. The stored quantization code for this vector +is the concatenation $2 || 1 || 4 || 3$. The original vector required $128$ dimensions $\times 32$-bit floats $ =4096$ bits total, +which has been compressed to $4$ chunks $\times 8$-bit integers $= 32$ bits of quantized storage. -### How RaBitQ works {#how-rabitq-works} +#### RaBitQ Quantization (RQ) -- Embeddings are grouped around centroids (as in other IVF indexes). -- Each residual vector is normalized and mapped to the nearest vertex of a randomly rotated hypercube on the unit sphere. -- The sign pattern of that vector is stored as bits (1 bit per dimension). -- Two small corrective factors are stored: - 1. The distance from the original vector to its centroid - 2. The dot product between the normalized vector and its quantized version +RaBitQ is an advanced quantization technique that outperforms PQ in several ways. +It needs no codebook to train, estimates distances very quickly at query-time, +and crucially, quantizes each vector in (with some small overhead) just **one bit per dimension!** +In practice, RaBitQ compresses a $1024$-dimensional `float32` vector into just a few thousand bits, while maintaining good recall. -Compared to `IVF_PQ`, RaBitQ: -- Avoids training expensive PQ codebooks -- Builds indexes faster and handles updates more easily -- Maintains or improves recall at high dimensionality under the same storage budget +The inner workings of RaBitQ quantization are rather mathematically dense. It generates a quantization codebook by +applying a uniformly random, approximately distance-preserving orthogonal transformation of the vertices of the $d$-dimensional hypercube, +where $d$ is the dimensionality of the dataset. We defer the details, and an elegant theoretical error bound, to [the original paper.](https://arxiv.org/pdf/2405.12497) -For a deeper dive into the theory and some benchmark results, see the blog post: [LanceDB's RaBitQ Quantization for Blazing Fast Vector Search](https://lancedb.com/blog/feature-rabitq-quantization/). +##### Using RaBitQ +Use RaBitQ quantization by selecting quantized index types ending in the suffix `RQ`. For example, call `create_index` with `index_type="IVF_RQ"`. +Note that when using `IVF_RQ`, the dimension of the dataset must be a multiple of `8`. -### Using RaBitQ {#using-rabitq} - -You can create an RaBitQ-backed vector index by setting `index_type="IVF_RQ"` when calling `create_index`. - - -When using `IVF_RQ`, vector dimensions must be divisible by `8`. - - -`num_bits` controls how many bits per dimension are used: - -1 bit is the classic RaBitQ setting. You can set it to 2, 4, or 8 bits to improve fidelity for better precision or recall — the main trade-off is additional storage for the extra bits per dimension, with only a modest increase in query-time compute. -It's also possible to tune the number of IVF partitions in `IVF_RQ`, similar to how you would do in `IVF_PQ`. +`num_bits` determines how many bits are used to quantize each dimension. +`1` is the standard RaBitQ setting. Increase to `2`, `4`, or `8` bits to achieve better recall for additional storage and query-time compute. -Indexes built with `num_bits >= 2` use an updated on-disk layout. Older LanceDB versions cannot read them and will fail with a clear missing-column error rather than returning incorrect results. Existing indexes keep working and upgrade automatically when they are rewritten (for example, during compaction, optimize, or remap). `num_bits=1` indexes are unaffected in both directions. +RaBitQ-quantized indexes computed with `num_bits >= 2` use a newer on-disk layout, and cannot be read by some older LanceDB versions. -## API Reference {#api-reference} +See this [blog post](https://lancedb.com/blog/feature-rabitq-quantization/) for further discussion and benchmarking of LanceDB's RaBitQ implementation. -The full list of parameters to the algorithm are listed below. +#### Scalar Quantization (SQ) +Scalar quantization quantizes each entry of a vector independently, by simply replacing it with the closest of a pre-defined set of values. +In practice, it often uses $8$ bits per dimension of a vector, and supports very fast encoding and decoding. -- `distance_type`: Literal["l2", "cosine", "dot"], defaults to "l2" - The distance metric to use for similarity comparison. Choose "l2" for Euclidean, "cosine" for cosine similarity, or "dot" for dot product. -- `num_partitions`: Optional[int], defaults to None - Number of IVF partitions (affects index build time and query accuracy). More partitions can improve recall but may increase build time. When unset, LanceDB chooses roughly the square root of the row count. -- `num_bits`: int, defaults to 1 - Bits per dimension for quantization (1 is standard RaBitQ). Higher values improve fidelity, mainly at the cost of additional storage. -- `max_iterations`: int, defaults to 50 - Maximum number of iterations for training the quantizer. Increase for larger datasets or to improve quantization quality. -- `sample_rate`: int, defaults to 256 - Number of samples per partition during training. Higher values may improve accuracy but increase training time. -- `target_partition_size`: Optional[int], defaults to None - Target number of vectors per partition. Adjust to control partition granularity and memory usage. If `num_partitions` is also set, `num_partitions` takes precedence. +For example, suppose we know all vector entires across our dataset lie in the range $[-128 \times 10^5, 127 \times 10^5]$. +In this case, we could quantize a given value $v$ as an $8$-bit representation of the integer $j$, where $j \times 10^5$ is the closest value to $v$ +among all integral multiples $\{j \times 10^5: -128 \leq j \leq 127 \}$. + +### Quantization API Reference + + +| Parameter | Description | +| :--- | :--- | +| `num_bits` | Bits per dimension for quantization. Only applies to `IVF_PQ`/`IVF_HNSW_PQ` (default `8`) and `IVF_RQ` (default `1`, RaBitQ) — not used by `IVF_FLAT`/`IVF_SQ`/`IVF_HNSW_FLAT`/`IVF_HNSW_SQ`. Higher values improve accuracy at the cost of additional storage. | + +`max_iterations` and `sample_rate` also affect quantizer training, but since they apply to every IVF/HNSW index type (not just quantized ones), they're documented as general [Build-time Parameters](/indexing/vector-index#build-time-parameters) instead. All three are passed as keyword arguments to `create_index`, alongside `index_type`: + + + + {QuantizationCustomParams} + + diff --git a/docs/web/integrations/lerobotdataset.mdx b/docs/web/integrations/lerobotdataset.mdx index 33c28cd49..70db08d3f 100644 --- a/docs/web/integrations/lerobotdataset.mdx +++ b/docs/web/integrations/lerobotdataset.mdx @@ -1,94 +1,159 @@ --- title: "LeRobotDataset" sidebarTitle: "LeRobotDataset" -description: "Use Lance-backed LeRobotDataset loaders and LanceDB to inspect, filter, and train on robotics datasets from the Hugging Face Hub." +description: "Train LeRobot policies straight from object storage, and curate, search and visualize robotics datasets as Lance tables." +keywords: ["lerobot", "robotics", "droid", "training", "dataloader"] --- import { PyFrameworksLerobotFilterFrames, - PyFrameworksLerobotLancedbImageDataset, - PyFrameworksLerobotLancedbVideoDataset, + PyFrameworksLerobotLoad, PyFrameworksLerobotOpenLanceTables, + PyFrameworksLerobotTrainReady, } from '/snippets/integrations.mdx'; -[LeRobot](https://huggingface.co/docs/lerobot/index) is Hugging Face's open-source robotics stack for collecting data, training policies, running simulations, and sharing robotics datasets and models on the Hub. +[LeRobot](https://huggingface.co/docs/lerobot/index) is Hugging Face's open-source robotics stack. Since [lerobot#4363](https://github.com/huggingface/lerobot/pull/4363) it reads Lance datasets natively: same `LeRobotDataset` class, same items, same training pipeline. The dataset's `"storage_format": "lance"` picks the reader. No subclasses, no wrapper library. -[LeRobotDataset v3.0](https://huggingface.co/docs/lerobot/lerobot-dataset-v3) standardizes robot learning data across sensorimotor time series, actions, multi-camera video, and task metadata. Its v3 layout stores high-frequency tabular signals in Parquet, visual streams as MP4 shards, and metadata that reconstructs episode-level views from larger files. +What you get: -Lance pairs well with LeRobot when you need high-performance random access, lazy multimodal blob reads, and a single table interface for curation, search, and training data preparation. The `lerobot-lancedb` package ships Lance-backed `LeRobotDataset` subclasses, and LanceDB can open Lance-formatted LeRobot datasets on the Hub directly through `hf://` URIs. +- **Train from object storage while keeping your GPUs fed.** Lance reads random frames straight from S3, GCS, the HF Hub or HF Storage Buckets, fetching only the bytes each batch needs, so every batch is a global shuffle: any frame, from anywhere in the dataset. In the table below (samples/s, 8 workers, batch 64), Lance and upstream local both draw every batch from the whole dataset. Upstream streaming does a reservoir shuffle, reading the dataset in order and drawing each batch from a pool of recently seen frames, so those two columns are not the same job: -## Install {#install} +| dataset | frames | cameras | Lance, S3 (global shuffle) | upstream, local (global shuffle) | same job | upstream, streaming (reservoir shuffle) | vs streaming | +|---|---|---|---|---|---|---|---| +| DROID | 27,630,375 | 3 | 2,258.5 | 346.7 | 6.5x | 898.6 | 1.7x | +| berkeley_rpt | 392,578 | 1 | 1,740.6 | 1,209.9 | 1.4x | 274.5 | 6.3x | +| toto | 325,699 | 1 | 1,097.0 | 936.3 | 1.2x | 121.3 | 9.0x | +| roboturk | 187,507 | 1 | 1,276.8 | 1,082.3 | 1.2x | 128.2 | 10.0x | +| aloha_mobile_cabinet | 127,500 | 3 | 815.7 | 294.2 | 2.8x | 77.7 | 10.5x | +| koch_pick_place | 37,972 | 2 | 854.7 | 274.9 | 3.1x | 58.1 | 14.7x | + +The gap grows with how much video each sample carries: about 1.2x with one camera, 2.8x with three, 6.5x on DROID. + +- **Faster iteration, end to end.** 10,000 steps of SmolVLA on DROID, 8xH100, lerobot's default `num_workers=4`, same seed: + +| | Lance, S3, nothing downloaded | upstream, local NVMe after a 384 GB download | +|---|---|---| +| wall clock | **1 h 27 m** | 2 h 00 m | +| steady rate | 495 samples/s | 361 samples/s | +| of each step spent waiting on data | 1.7% | 37.4% | +| final loss | 0.2380 | 0.2380 | + +Same model, same loss, 33 minutes sooner, and no 384 GB download first. The difference is time the GPUs spend waiting on data, so it grows with the run: at 100k steps it is over five hours, and every re-run and sweep point pays it again. + +- **The training table is also the index.** Parquet has no secondary indexes, so finding frames instead of scanning them usually means another system per question: a vector database for embeddings, a search service for instructions, a feature store for scores. With Lance those are columns and indexes on the same table the DataLoader reads. One query spans all of them, at a version the trainer can reopen. + +## Install ```bash -pip install lancedb lance lerobot-lancedb +pip install "lerobot[lancedb]" # the reader, inside lerobot itself +pip install lerobot-lancedb # the converter ``` -## Use Lance-backed LeRobotDataset loaders {#use-lance-backed-lerobotdataset-loaders} +## Convert a dataset -`LeRobotLanceDataset` is useful when your Lance-backed dataset stores decoded image observations. It's a drop-in replacement for `LeRobotDataset`, so existing policy training code keeps working with the usual PyTorch dataset and dataloader patterns. +Any LeRobot v3.0 dataset, from the Hub or a local directory: + +```bash +lerobot-lance-convert --repo-id lerobot/pusht --out ./pusht-lance +``` + +**Migration costs about as much as a file copy.** Videos are stored as blobs without re-encoding, so items are bit-identical to the source: 392,578 frames convert in 10 seconds, DROID's 27.6M in 34 minutes. Nothing about your recording or training code changes. The output keeps `meta/` as is and adds three Lance tables (`frames`, `videos`, `meta`). `lerobot-lance-doctor` audits the result and often finds problems in the source: DROID carries 44% orphaned rows, and three of eight public datasets we converted have frame-count defects that only random access exposes. + +Host the result anywhere: an HF dataset repo (`hf upload`, tag it `v3.0`), an HF Storage Bucket (`hf buckets sync`), or any object store (`aws s3 sync`). + +## Load and train - {PyFrameworksLerobotLancedbImageDataset} + {PyFrameworksLerobotLoad} -For datasets that store camera observations as MP4 video segments, use `LeRobotLanceVideoDataset` instead. +An explicit `root` works for any object store: `LeRobotDataset("lerobot/pusht", root="s3://my-bucket/pusht-lance")`. Remote roots download only `meta/`. Data is fetched per batch. Temporal windows, `DataLoader` and the rest of the training stack work unchanged: - {PyFrameworksLerobotLancedbVideoDataset} + {PyFrameworksLerobotTrainReady} - -Use the image loader for Lance-backed repos that store image frames. Use the video loader for MP4-backed LeRobot datasets such as `lance-format/lerobot-pusht-lance`. - +Or from the CLI. Held-out evaluation on a remote dataset needs random access, so it only works on the Lance path: -## Open LeRobot Lance tables with LanceDB {#open-lerobot-lance-tables-with-lancedb} +```bash +lerobot-train \ + --dataset.repo_id=my-org/my-bucket/pusht-lance \ + --dataset.repo_type=bucket \ + --dataset.eval_split=0.02 \ + --policy.type=act +``` -Lance-formatted LeRobot datasets published by `lance-format` expose each `.lance` file under `data/` as a LanceDB table. The PushT dataset, for example, has `frames`, `episodes`, and `videos` tables. +## Visualize TB-scale datasets in Foxglove + +LeRobot's dataset viewer can serve an episode to [Foxglove](https://foxglove.dev) over its WebSocket protocol ([lerobot#4542](https://github.com/huggingface/lerobot/pull/4542)), and with a Lance dataset it works wherever the data lives: + +```bash +lerobot-dataset-viz --repo-id lance-format/pusht-lance --episode-index 3 --display-mode foxglove +``` + +Open the Foxglove app, connect to `ws://localhost:8765`, and scrub. Cameras, joint state and actions show up as topics you can lay out however you like: + +![Foxglove showing episode 7 of DROID served from S3: three camera panels and the joint state, scrubbed to 19.4 s](/static/assets/images/integrations/lerobot-foxglove-droid.png) + +Frames are fetched as you scrub, so looking at one episode of the 373 GB DROID from S3 moves a few MB, not the dataset. No MCAP export, no download, and nothing new to install on the dataset side: this is the same reader the trainer uses. + +## Query, curate, enrich + +The frames table is a LanceDB table like any other: {PyFrameworksLerobotOpenLanceTables} -Opening the tables directly is handy for inspecting schemas, counting rows, sampling metadata, or building curation workflows before any data reaches the training loop. - -## Filter a frame window {#filter-a-frame-window} - -Most robotics workflows want a deterministic slice by `episode_index`, `frame_index`, or task metadata long before training begins. LanceDB filters those rows without touching the video blobs. +Filter with SQL over any feature, using the indexes built at conversion: {PyFrameworksLerobotFilterFrames} -With the filtered set in hand, you can materialize a smaller local LanceDB database, add derived columns, attach embeddings, or build vector and scalar indexes for faster repeated access. +From here it is standard LanceDB. The examples below are from our DROID walkthrough, all on the table the trainer reads. -## Example Lance-formatted LeRobot datasets {#example-lance-formatted-lerobot-datasets} +**Feature engineering costs nothing until you use it.** A new column is a [declaration](/feature-engineering/add-computed-column): `add_columns` registers the expression or [function](/management/function) and computes nothing, and a [refresh](/feature-engineering/refresh-column) materializes it in parallel when you want it. No copy of the dataset, and the videos are never touched: - - - A Lance-formatted version of `lerobot/pusht` with frame, episode, and video tables. - - - A multi-camera robotics dataset packaged as Lance tables for frame-level and episode-level access. - - +```python +@udf(data_type=pa.float32(), input_columns=["action_joint_velocity"]) +def jerk_score(v): # per-frame motion roughness + ... -## More resources {#more-resources} +tbl.add_columns({"jerk_score": jerk_score}) # nothing computed yet +tbl.backfill("jerk_score", concurrency=8) # 610,403 rows in 16.7 s +``` - - - Hugging Face's guide to the v3 dataset layout, streaming, transforms, and migration. - - - API documentation for the Lance-backed LeRobotDataset implementations. - - +Embeddings work the same way, reading frames straight from the video blobs in the same table: -## When to use each interface {#when-to-use-each-interface} +```python +@udf(data_type=pa.list_(pa.float32(), 768), num_gpus=1, + input_columns=["episode_index", "frame_index"]) +class EmbedFromBlob: # SigLIP2 loads once per worker + def __call__(self, episode_index, frame_index): + blob = self.videos.take_blobs("video_bytes", indices=[vrow])[0] + frame = VideoDecoder(blob).get_frames_at([pos]).data[0] + ... +``` -| Interface | Best for | -|:---|:---| -| `LeRobotDataset` | Standard LeRobot training loops and policy code | -| `LeRobotLanceDataset` | Drop-in training on Lance-backed image datasets | -| `LeRobotLanceVideoDataset` | Drop-in training on Lance-backed video datasets | -| LanceDB | Interactive inspection, filtering, curation, search, indexing, and materializing subsets | -| `lance.dataset(...)` | Lower-level schema, fragment, index, and blob access | +**Search** is an index on those columns: a vector index over the embeddings built in 29.7 s across 27.6M rows, a full-text index over the instructions in 7.0 s, queries in 10 to 54 ms. + +**Curation** is one query across all of it. Semantic search with a predicate on the derived score, no join, no second system: + +```python +tbl.search(vec("a gripper closing on an object"), vector_column_name="emb_siglip2") \ + .where("jerk_score > 1.2875") # the roughest 1% of frames + .limit(4) +``` + +**Mining** is the same query pointed at the rare cases. `tbl.search().where("jerk_score > 1.2875 AND success = false")` pulls the rough, failed frames out of 27.6M rows in milliseconds, ready to become a fine-tuning set or a labeling queue. + +**EDA** is a scan of the tabular columns: a pass over all 27.6M rows reads 2.52 GB in 190 s and decodes no video. + +Then drop what you found from training with `episodes=[...]` instead of rewriting files. The reader ignores columns it does not know, and the table is versioned, so curation and training share one copy of the data at a version you can reopen. + + +Lance datasets are read-only in LeRobot: record and edit in the default format, then convert. + + +Public examples to try everything above: [`lance-format/pusht-lance`](https://huggingface.co/datasets/lance-format/pusht-lance) and friends under the [`lance-format`](https://huggingface.co/lance-format) org. diff --git a/docs/web/management/view.mdx b/docs/web/management/view.mdx new file mode 100644 index 000000000..9db9e8a08 --- /dev/null +++ b/docs/web/management/view.mdx @@ -0,0 +1,32 @@ +--- +title: "Views" +sidebarTitle: "View" +description: "A saved query, evaluated when read. The non-materialized counterpart to a materialized view." +icon: eye +keywords: ["view", "create view", "sql", "catalog"] +--- + +Enterprise + +This page describes a LanceDB Enterprise capability. The embedded form +of LanceDB has no server to provide it -- see +[Architecture](/architecture) for what differs between the two. + +A view stores a **query**, not rows. Reading it runs the query against current +data, so a view is never stale -- and never faster than the query it wraps. + +It is the counterpart to a +[materialized view](/management/materialized-view), which stores rows and is +brought up to date by a refresh. Both are [catalog objects](/basics/catalog) +defined by a query; the difference is entirely when that query runs. + +| | View | Materialized view | +| --- | --- | --- | +| Stores | the query | the rows | +| Freshness | always current | as of the last refresh | +| Read cost | the full query, every read | a table scan | +| Write cost | none | a refresh | + +Views are created in SQL, over the [Flight SQL endpoint](/search/sql) -- there +is no SDK method, because the thing a view stores *is* a SQL statement. See +[DDL](/sql/ddl#views). diff --git a/docs/web/quickstart.mdx b/docs/web/quickstart.mdx index 2e38402e3..aff71bc71 100644 --- a/docs/web/quickstart.mdx +++ b/docs/web/quickstart.mdx @@ -491,7 +491,7 @@ permutation = Permutation.identity(characters) dataloader = torch.utils.data.DataLoader(permutation) ``` -See [Training](/training) for shuffling, multi-worker loading, and reading from +See [Training](/training/data-loading) for shuffling, multi-worker loading, and reading from a remote table. ## Code {#code} @@ -535,7 +535,7 @@ full-text and hybrid search, reranking, and server-side feature engineering. Use LanceDB for projected, shuffled, random-access reads in training workflows. diff --git a/docs/web/search/sql/fts-sql.mdx b/docs/web/search/sql/fts-sql.mdx new file mode 100644 index 000000000..836f724d8 --- /dev/null +++ b/docs/web/search/sql/fts-sql.mdx @@ -0,0 +1,32 @@ +--- +title: "Full-text search with SQL" +sidebarTitle: "Full-Text Search" +description: "Running full-text search from SQL, with fuzzy, phrase, boolean and boost queries." +icon: magnifying-glass +keywords: ["fts", "sql", "full text search", "fuzzy", "phrase"] +--- + +Enterprise + +This page describes a LanceDB Enterprise capability. The embedded form +of LanceDB has no server to provide it -- see +[Architecture](/architecture) for what differs between the two. + +Full-text search is available in SQL as the [`fts()`](/sql/functions#fts) table +function, which returns matching rows plus a `_score` column: + +```sql +SELECT id, text, _score +FROM fts('my_docs', 'puppy') +ORDER BY _score DESC +LIMIT 5 +``` + +The second argument is a bare query string, or a JSON query object for the +fuzzy, phrase, boolean, boost and multi-match forms. + +For a keyword test that needs no score, +[`contains_tokens`](/sql/scalar-functions#contains-tokens) is a predicate usable +directly in `WHERE`, and is accelerated by the full-text index. + +The query-builder equivalent is [Full-Text Search](/search/full-text-search). diff --git a/docs/web/search/sql/index.mdx b/docs/web/search/sql/index.mdx new file mode 100644 index 000000000..06b46b717 --- /dev/null +++ b/docs/web/search/sql/index.mdx @@ -0,0 +1,29 @@ +--- +title: "Connecting a SQL client" +sidebarTitle: "Client Connection" +description: "Reaching the Arrow Flight SQL endpoint from Python or TypeScript." +icon: plug +keywords: ["flight sql", "client", "connect", "arrow"] +--- + +Enterprise + +This page describes a LanceDB Enterprise capability. The embedded form +of LanceDB has no server to provide it -- see +[Architecture](/architecture) for what differs between the two. + +SQL is served over an +[Arrow Flight SQL](https://arrow.apache.org/docs/format/FlightSql.html) +endpoint, so any Flight SQL client reaches it and results arrive as Arrow +record batches. + +From Python, the connection runs SQL directly without a separate client: + +```python +reader = db.execute_query("SELECT id, text FROM my_docs LIMIT 10") +table = reader.read_all() +``` + +The TypeScript SDK has no SQL method; use a Flight SQL client. See +[SDKs and SQL](/basics/apis) for the full comparison, and the +[SQL reference](/sql) for the dialect. diff --git a/docs/web/search/vector-search.mdx b/docs/web/search/vector-search.mdx index 619163841..e1e82045a 100644 --- a/docs/web/search/vector-search.mdx +++ b/docs/web/search/vector-search.mdx @@ -53,7 +53,7 @@ Raw data (e.g. text, images, audio, etc.) is converted into embeddings via an em Vector search has **no SQL form**. Run it here and use [SQL](/sql) over the result. -## Supported distance metrics {#supported-distance-metrics} +## Supported distance metrics Distance metrics determine how LanceDB compares vectors to find similar matches. Euclidean or `l2` is the default, and used for general-purpose similarity, `cosine` for unnormalized embeddings, `dot` for normalized embeddings (best performance), or `hamming` for binary vectors. @@ -65,10 +65,10 @@ The right metric improves both search accuracy and query performance. Currently, | Distance metric | Mathematical form | Notes | |---|---|---| -| `l2` | $\|x-y\|_2=\sqrt{\sum_i (x_i-y_i)^2}$ | Measures the straight-line distance between two points in vector space. Calculated as the square root of the sum of squared differences between corresponding vector components. | -| `cosine` | $1-\frac{x\cdot y}{\|x\|_2\|y\|_2}$ | Measures directional difference between vectors. Computed as 1 minus cosine similarity (the dot product normalized by both vector magnitudes), so vector length does not affect the score. Use for unnormalized vectors. | -| `dot` | $x\cdot y=\sum_i x_i y_i$ | Calculates the sum of products of corresponding vector components. Provides raw similarity scores without normalization, sensitive to vector magnitudes. Use for normalized vectors for best performance. | -| `hamming` | $\sum_i \mathbf{1}[x_i\neq y_i]$ | Counts the number of positions where corresponding bits differ between binary vectors. Only applicable to binary vectors stored as packed uint8 arrays. | +| `l2` | $$\|x-y\|_2= \sqrt{\sum_i (x_i-y_i)^2}$$ | The $\ell_2$ norm. Measures Euclidean distance between two points in geometric space. | +| `cosine` | $1-\frac{x\cdot y}{\|x\|_2\|y\|_2}$ | Measures directional difference between vectors. Insensitive to nonzero scaling of vectors. | +| `dot` | $x\cdot y= \underset{i}{\sum} x_i y_i$ | The standard dot product of real vectors. Sensitive to nonzero scaling of vectors; use on normalized vectors. | +| `hamming` | $\underset{i}{\sum} \,\: \mathbf{1}_{\, [x_i\neq y_i]}$ | Counts the number of bitwise-differing bits between binary vectors. | For indexed search, supported distance metrics vary by index type: @@ -82,12 +82,20 @@ For indexed search, supported distance metrics vary by index type: | `IVF_HNSW_PQ` | `["l2", "cosine", "dot"]` | | `IVF_HNSW_SQ` | `["l2", "cosine", "dot"]` | -### Configure Distance Metric {#configure-distance-metric} +### Configure Distance Metric -By default, `l2` will be used as metric type. You can specify the metric type as -`cosine` or `dot` if required (`hamming` is supported for `IVF_FLAT` index only). +Without a vector index, searches use `l2` by default. You can specify `cosine` or +`dot` instead (`hamming` is supported for `IVF_FLAT` indexes only). -**Note:** You can configure the distance metric during search only if there's no vector index. If a vector index exists, the distance metric will always be the one you specified when creating the index. +When a vector index exists, the search metric must match the metric used to build +the index. If you explicitly request a different metric, LanceDB cannot use that +index and falls back to an exhaustive (brute-force) search. On LanceDB Cloud, the +brute-force KNN safety limit can reject that search on a large table instead of +executing it. LanceDB Enterprise doesn't have the limit. + +If you omit the search metric, current SDKs use the index metric when an index is +available. Some older SDK versions sent `l2` when the metric was omitted; with a +non-`l2` index, explicitly set the matching metric or upgrade the SDK. @@ -103,11 +111,14 @@ By default, `l2` will be used as metric type. You can specify the metric type as -Here you can see the same search but using `cosine` similarity instead of `l2` distance. The result focuses on vector direction rather than absolute distance, which works better for normalized embeddings. +Here you can see the same search but using `cosine` similarity instead of `l2` +distance. If the table has a vector index, make sure it was also built with +`cosine`. The result focuses on vector direction rather than absolute distance, +which works better for unnormalized embeddings. Set `.limit(...)` on vector searches you run in applications. You can page through results with `.offset(...)` and include LanceDB's internal row id with `.with_row_id()` / `.withRowId()` when you need a stable handle for follow-up operations. -## Selecting the vector column {#selecting-the-vector-column} +## Selecting the vector column If your table has exactly one vector column, you can omit the column name and LanceDB will pick it for you. This works for both top-level columns (such as `vector`) and vector fields nested inside a struct (such as `image.embedding`). @@ -142,7 +153,7 @@ The same field-path syntax works when creating an index on a nested vector colum When several columns share a name across structs (for example, `image.embedding` and `text.embedding`), LanceDB still picks the one whose dimension matches your query vector. If two candidates have the same dimension, you must pass the column name explicitly. -## Vector Search With ANN Index {#vector-search-with-ann-index} +## Vector Search With ANN Index Instead of performing an exhaustive search on the entire database for each and every query, approximate nearest neighbour (ANN) algorithms use an index to narrow down the search space, which significantly reduces query latency. @@ -154,7 +165,7 @@ Use ANN search for large-scale applications where speed matters more than perfec When a vector index is used, `_distance` is not always the true distance between full vectors. On quantized ANN indexes, LanceDB may compute `_distance` from the compressed representation for speed. Use `refine_factor` when you want reranking on full vectors. -### Exact vs Approximate Distances {#exact-vs-approximate-distances} +### Exact vs Approximate Distances When doing vector search, the meaning of "distance" depends on whether you are using an index and whether `refine_factor` is specified as part of your query. `nprobes` controls how many partitions are searched to find candidates, `approx_mode` controls the query-time speed/recall trade-off for RQ-quantized indexes, and `refine_factor` controls how many candidates are rescored on full vectors for better distance fidelity and reranking quality. @@ -185,7 +196,7 @@ The table below summarizes the behavior of `_distance` in search results based o For deeper tuning guidance on indexing and performance estimation, see the [vector indexes](/indexing/vector-index/#search-configuration) page, For tuning `nprobes`, see below. -### Tuning approximate mode {#tuning-approximate-mode} +### Tuning `approx_mode` Use `approx_mode` when you want to adjust the speed/recall trade-off for approximate vector search at query time. This setting currently applies only to RQ-quantized indexes, such as `IVF_RQ`; other index types ignore it. @@ -199,7 +210,7 @@ The supported values are: You can change `approx_mode` per query without rebuilding the index. For RQ indexes built with `num_bits=1`, `normal` uses the same one-bit scoring path as `fast`. If you also set `refine_factor`, LanceDB first uses `approx_mode` while finding candidates, then reranks the selected candidates on full vectors. -### Tuning `nprobes` {#tuning-nprobes} +### Tuning `nprobes` - `nprobes` controls how many partitions are searched at query time. - `nprobes` improves candidate recall, but does not by itself make `_distance` exact. @@ -213,7 +224,7 @@ For filtered ANN searches, you can also set `minimum_nprobes` and `maximum_nprob with the minimum and can scan more partitions up to the maximum if the filter leaves too few candidates. Calling `nprobes(n)` fixes both values to `n`, which disables that adaptive behavior. -### Vector Search with Prefiltering {#vector-search-with-prefiltering} +### Vector Search with Prefiltering This is the default vector search setting. You can use prefiltering to boost query performance by reducing the search space before vector calculations begin. The system first applies your filter criteria to the dataset, then conducts vector search operations only on the remaining relevant subset. @@ -237,7 +248,7 @@ The `.where("label > 2")` applies a filter before vector search, `.select(["text As a result, you'll see a result with just the data you want from the most similar vectors. -### Vector Search with Postfiltering {#vector-search-with-postfiltering} +### Vector Search with Postfiltering Use postfiltering to prioritize vector similarity by searching the full dataset first, then applying metadata filters to the top results. This approach ensures you get the most similar vectors before filtering, which can be crucial when similarity is more important than metadata constraints. @@ -266,7 +277,7 @@ In the end, you receive a query result with the best matches that also meet your the filter condition after obtaining the nearest neighbors based on vector similarity. -## Multivector Search {#multivector-search} +## Multivector Search Use multivector search when your documents contain multiple embeddings and you need sophisticated matching between query and document vector pairs. The late interaction approach finds the most relevant combinations across all available embeddings and provides nuanced similarity scoring. @@ -283,9 +294,9 @@ Here you can see how to take 2 query vectors and find the best matching pairs be **Read more:** [Multivector search](/search/vector-search) -## Advanced Search Scenarios {#advanced-search-scenarios} +## Advanced Search Scenarios -### Search With Distance Range {#search-with-distance-range} +### Search With Distance Range Use `distance_range` search when you need vectors within particular similarity bounds rather than just the closest neighbors. The system filters results to only include vectors that fall within your specified distance thresholds from the query. @@ -309,7 +320,7 @@ The `distance_range()` method filters results by similarity thresholds - the fir Each approach returns Arrow tables with vectors that fall within your specified distance thresholds. -### Search With Binary Vectors {#search-with-binary-vectors} +### Search With Binary Vectors Use binary vector search for scenarios involving binary embeddings, such as those produced by hashing algorithms. The system stores these efficiently as packed uint8 arrays and uses Hamming distance calculations to determine vector similarity. @@ -337,9 +348,9 @@ The schema defines a 32-byte vector field (256 bits ÷ 8), `np.random.randint(0, The search produces an Arrow table with binary vectors ranked by how many bits differ from the query. -## Scaling Vector Search {#scaling-vector-search} +## Scaling Vector Search -### Batch Search {#batch-search} +### Batch Search Use batch search to handle multiple query vectors simultaneously. This gives you significant efficiency gains over individual queries. LanceDB processes all vectors in parallel and organizes results with a `query_index` field that maps each result set back to its originating query. @@ -369,7 +380,7 @@ to explicitly associate each result set with its corresponding query in the input batch. -### Search With Asynchronous Indexing {#search-with-asynchronous-indexing} +### Search With Asynchronous Indexing To optimize for speed over completeness, enable the `fast_search` flag in your query to skip searching unindexed data. @@ -398,9 +409,9 @@ The `fast_search=True` parameter tells LanceDB to only search indexed vectors, s You'll obtain a query result with the top `5` matches from indexed vectors, but might miss data that was just added. -## Brute Force Search {#brute-force-search} +## Brute Force Search -### Search With No Index {#search-with-no-index} +### Search With No Index The simplest way to perform vector search is to perform a brute force search, without an index, where the distance between the query vector and all the vectors in the database are computed, with the top-k closest vectors returned. @@ -428,7 +439,7 @@ This carries out a brute force search through every vector in the table to find As you can imagine, the brute force approach is not scalable for datasets larger than a few hundred thousand vectors, as the latency of the search grows linearly with the size of the dataset. This is where approximate nearest neighbour (ANN) algorithms come in. -### Bypass the Vector Index {#bypass-the-vector-index} +### Bypass the Vector Index Use `bypass_vector_index` to get exact, ground-truth results by performing exhaustive searches across all vectors. Instead of relying on approximate methods, the system directly compares your query against every vector in the table, ensuring 100% recall at the cost of increased query time. @@ -457,13 +468,15 @@ This approach is particularly useful when: - Calculating recall metrics to tune index parameters - Ensuring exact results for critical applications +## Multi-vector search {#multivector} + LanceDB's multivector support enables you to store and search multiple vector embeddings for a single item. This capability is particularly valuable when working with late-interaction models like ColBERT and ColPaLi, which generate multiple embeddings per document. In this tutorial, you'll create a table with multiple vector embeddings per document and learn how to perform multivector search. For more end-to-end examples, see the [VectorDB recipes repository](https://github.com/lancedb/vectordb-recipes/tree/main/examples). -## Multivector Support {#multivector-support} +### Multivector Support Each item in your dataset can have a column containing multiple vectors, which LanceDB can efficiently index and search. When performing a search, you can query with either a single vector embedding or multiple vector embeddings. @@ -473,7 +486,7 @@ Currently, only the `cosine` metric is supported for multivector search. The vec Each query vector must match the inner vector dimension in the multivector column. This applies to both single-vector queries and multi-vector query matrices. -## Computing Similarity {#computing-similarity} +### Computing Similarity MaxSim (Maximum Similarity) is a key concept in late-interaction models that: @@ -495,9 +508,9 @@ $$ $Q$ represents the query embeddings, and $D = \{d_1, d_2, ..., d_{|D|}\}$ represents the document embeddings. -## Using Multivector Search {#using-multivector-search} +### Using Multivector Search -### 1\. Setup {#1-setup} +#### 1. Setup Connect to LanceDB and import the required libraries. @@ -515,7 +528,7 @@ db = lancedb.connect( ``` -### 2\. Define Schema {#2-define-schema} +#### 2. Define Schema Define a schema that specifies a multivector field. A multivector field is a nested list structure in which each document contains multiple vectors. In this case, we'll create a schema with: @@ -538,7 +551,7 @@ schema = pa.schema( ``` -### 3\. Generate Multivectors {#3-generate-multivectors} +#### 3. Generate Multivectors Generate sample data where each document contains multiple vector embeddings, which can represent different aspects or views of the same document. @@ -556,7 +569,7 @@ data = [ ``` -### 4\. Create a Table {#4-create-a-table} +#### 4. Create a Table Create a table with the defined schema and sample data, which will store multiple vectors per document for similarity search. @@ -566,7 +579,7 @@ tbl = db.create_table("multivector_example", data=data, schema=schema) ``` -### 5\. Build an Index {#5-build-an-index} +#### 5. Build an Index Only cosine similarity is supported for multivector search operations. For faster search, build the standard `IVF_PQ` index over your vectors: @@ -583,10 +596,10 @@ tbl.create_index(metric="cosine", vector_column_name="vector") A brute-force scan over a multivector column has to compare every query vector to every document vector in every row, so the cost grows with both the row count and the number of vectors per row. In LanceDB OSS, the query will just run, so a large unindexed multivector table can stall a process for a long time before returning results. -On LanceDB Enterprise, the brute-force KNN safety check applies a stricter row threshold to multivector columns — roughly 10× lower than for single-vector columns. So an unindexed multivector table will start being rejected with a "vector search would use brute-force KNN" error well before a comparable single-vector table would. Build the index before you start hitting it from production traffic, even if the dataset is small enough that you'd skip indexing for a single-vector workload. +On LanceDB Cloud, the brute-force KNN safety check applies a stricter row threshold to multivector columns — roughly 10× lower than for single-vector columns. So an unindexed multivector table can be rejected with a "vector search would use brute-force KNN" error well before a comparable single-vector table would. LanceDB Enterprise doesn't have the limit. Build the index before you start hitting it from production traffic, even if the dataset is small enough that you'd skip indexing for a single-vector workload. -### 6\. Query a Single Vector {#6-query-a-single-vector} +#### 6. Query a Single Vector When searching with a single query vector, it will be compared against all vectors in each document, and the similarity scores will be aggregated to find the most relevant documents. @@ -597,7 +610,7 @@ results_single = tbl.search(query).limit(5).to_pandas() ``` -### 7\. Query Multiple Vectors {#7-query-multiple-vectors} +#### 7. Query Multiple Vectors With multiple query vectors, LanceDB calculates similarity using late interaction, a late-interaction technique that computes relevance by finding the best-matching pairs between query and document vectors. This approach provides more nuanced matching while maintaining fast retrieval speeds. @@ -611,7 +624,7 @@ results_multi = tbl.search(query_multi).limit(5).to_pandas() Visit the [Hugging Face embedding integration](/integrations/embedding/huggingface/) page for information on embedding models. -## Simple Example: ColBERT Embeddings {#simple-example-colbert-embeddings} +### Simple Example: ColBERT Embeddings [ColBERT](https://arxiv.org/abs/2004.12832) is the most well-known late-interaction retrieval model that represents each document and query as multiple token embeddings and scores matches by taking the best @@ -630,14 +643,14 @@ import pyarrow as pa import lancedb from pylate import models -# 1) Load a late-interaction model via PyLate -# PyLate docs show ColBERT() + encode(..., is_query=...) :contentReference[oaicite:2]{index=2} +## 1) Load a late-interaction model via PyLate +## PyLate docs show ColBERT() + encode(..., is_query=...) :contentReference[oaicite:2]{index=2} model = models.ColBERT(model_name_or_path="lightonai/GTE-ModernColBERT-v1") -# You can discover dim from one embedding (avoid guessing) +## You can discover dim from one embedding (avoid guessing) dim = model.encode(["hello"], is_query=True)[0].shape[1] -# 2) Create a LanceDB table with a multivector column +## 2) Create a LanceDB table with a multivector column db = lancedb.connect("./pylate_lancedb") schema = pa.schema([ pa.field("doc_id", pa.string()), @@ -652,7 +665,7 @@ docs = [ {"doc_id": "3", "text": "This is a noodle bar in Osaka, Japan."}, ] -# 3) Encode documents with PyLate (token vectors per doc) +## 3) Encode documents with PyLate (token vectors per doc) doc_texts = [d["text"] for d in docs] doc_embs = model.encode(doc_texts, is_query=False) # list/array of (T, dim) per doc :contentReference[oaicite:4]{index=4} @@ -663,10 +676,10 @@ for d, emb in zip(docs, doc_embs): tbl = db.create_table("docs", data=rows, schema=schema, mode="overwrite") -# 4) Build an index + query using a query matrix. -# Multivector brute-force scales with rows × vectors-per-row, so build the index -# at much smaller dataset sizes than you would for single-vector search — and -# always before exposing the table to remote traffic. +## 4) Build an index + query using a query matrix. +## Multivector brute-force scales with rows × vectors-per-row, so build the index +## at much smaller dataset sizes than you would for single-vector search — and +## always before exposing the table to remote traffic. tbl.create_index(vector_column_name="mv", metric="cosine") query = "Tell me about ramen in Japan" @@ -680,7 +693,7 @@ print(out[["doc_id", "text"]]) Late-interaction model implementations evolve rapidly, so it's a good idea to check the latest popular models when trying multivector search. -## Advanced Example: XTR Embeddings {#advanced-example-xtr-embeddings} +### Advanced Example: XTR Embeddings [ConteXtualized Token Retriever (XTR)](https://arxiv.org/abs/2304.01982) is a late-interaction retrieval model that represents text as token-level vectors instead of a single embedding. This lets search score token-to-token matches (MaxSim), which can improve fine-grained relevance. diff --git a/docs/web/snippets/indexing.mdx b/docs/web/snippets/indexing.mdx index 278a097ec..a26cb1c0c 100644 --- a/docs/web/snippets/indexing.mdx +++ b/docs/web/snippets/indexing.mdx @@ -12,6 +12,8 @@ export const PyGpuIndexCuda = "table.create_index(\n num_partitions=256,\n export const PyGpuIndexMps = "table.create_index(\n num_partitions=256,\n num_sub_vectors=96,\n accelerator=\"mps\",\n)\n"; +export const PyQuantizationCustomParams = "table.create_index(\n index_type=\"IVF_RQ\",\n num_bits=2,\n max_iterations=100,\n sample_rate=512,\n)\n"; + export const PyReindexingIncremental = "table = db.open_table(\"reindexing_incremental\")\ntable.add([{\"vector\": [3.1, 4.1], \"text\": \"Frodo was a happy puppy\"}])\ntable.optimize()\n"; export const PyScalarIndexBuild = "tbl = db.open_table(\"scalar_index_build\")\ntbl.create_scalar_index(\"book_id\")\ntbl.create_scalar_index(\"publisher\", index_type=\"BITMAP\")\n"; @@ -38,24 +40,14 @@ export const PyScalarIndexWait = "index_name = \"label_idx\"\ntable.wait_for_ind export const PyVectorIndexAsyncConfig = "import lancedb\nimport numpy as np\nfrom lancedb.index import IvfPq\n\nasync def main():\n data = [\n {\"id\": i, \"vector\": np.random.random(8).astype(np.float32).tolist()}\n for i in range(512)\n ]\n\n db = await lancedb.connect_async(\"ex_lancedb\")\n table = await db.create_table(\n \"vector_index_async\", data=data, mode=\"overwrite\"\n )\n\n await table.create_index(\n \"vector\",\n config=IvfPq(\n distance_type=\"cosine\",\n num_partitions=16,\n num_sub_vectors=4,\n ),\n )\n return await table.list_indices()\n"; -export const PyVectorIndexBinaryAddData = "table.add(data)\n"; - -export const PyVectorIndexBinaryBuildIndex = "table.create_index(\n metric=\"hamming\",\n vector_column_name=\"vector\",\n index_type=\"IVF_FLAT\",\n)\n"; - -export const PyVectorIndexBinarySchema = "table = tmp_db.create_table(table_name, schema=schema, mode=\"overwrite\")\n"; - -export const PyVectorIndexBinarySearch = "query = np.random.randint(0, 2, size=ndim)\nquery = np.packbits(query)\ndf = table.search(query).metric(\"hamming\").limit(10).to_pandas()\ndf.vector = df.vector.apply(np.unpackbits)\n"; - export const PyVectorIndexBuildHnsw = "table.create_index(index_type=\"IVF_HNSW_SQ\")\n"; -export const PyVectorIndexBuildIvf = "table_name = \"vector-index-build-ivf\"\ntable = db.open_table(table_name)\ntable.create_index(\n metric=\"cosine\",\n vector_column_name=\"keywords_embeddings\",\n)\n"; +export const PyVectorIndexBuildIvf = "table_name = \"vector-index-build-ivf\"\ntable = db.open_table(table_name)\ntable.create_index(\n metric=\"cosine\",\n vector_column_name=\"keywords_embeddings\",\n index_type=\"IVF_PQ\",\n)\n"; export const PyVectorIndexBypassRecall = "query = np.random.random(128)\nk = 10\n\n# Ground truth: flat (exhaustive) scan, ignoring the ANN index.\ntruth = set(table.search(query).bypass_vector_index().limit(k).to_pandas()[\"id\"])\n\n# ANN results with the current nprobes setting.\nann = set(table.search(query).nprobes(20).limit(k).to_pandas()[\"id\"])\n\nrecall_at_k = len(truth & ann) / k\n"; export const PyVectorIndexCheckStatus = "index_name = \"keywords_embeddings_idx\"\ntable.wait_for_index([index_name])\nprint(table.index_stats(index_name))\n"; -export const PyVectorIndexConfigureIvf = "table.create_index(metric=\"l2\", num_partitions=16, num_sub_vectors=4)\n"; - export const PyVectorIndexCustomName = "# Override the default `{column}_idx` convention by passing `name=...`.\ntable.create_index(\n metric=\"cosine\",\n vector_column_name=\"keywords_embeddings\",\n name=\"my_custom_index\",\n)\ntable.wait_for_index([\"my_custom_index\"])\nprint(table.index_stats(\"my_custom_index\"))\n"; export const PyVectorIndexDistanceRange = "# Only return results whose distance falls within [0.0, 0.5).\n# Useful for near-duplicate detection or thresholded similarity search.\n(\n table.search(np.random.random(128))\n .distance_range(lower_bound=0.0, upper_bound=0.5)\n .limit(10)\n .to_pandas()\n)\n"; @@ -68,5 +60,3 @@ export const PyVectorIndexQueryHnsw = "tbl = table\ntbl.search(np.random.random( export const PyVectorIndexQueryIvf = "tbl = table\ntbl.search(np.random.random((1536))).limit(2).nprobes(20).refine_factor(\n 10\n).to_pandas()\n"; -export const PyVectorIndexSetup = "table_name = \"vector-index-tbl\"\ntable = db.open_table(table_name)\n"; - diff --git a/docs/web/snippets/integrations.mdx b/docs/web/snippets/integrations.mdx index de11f10ad..67c48ad88 100644 --- a/docs/web/snippets/integrations.mdx +++ b/docs/web/snippets/integrations.mdx @@ -74,11 +74,11 @@ export const PyFrameworksLangchainVectorStoreConfig = "db_url = \"db://lang_test export const PyFrameworksLerobotFilterFrames = "frame_rows = (\n frames.search()\n .where(\"episode_index = 0 AND frame_index < 10\", prefilter=True)\n .select([\"episode_index\", \"frame_index\", \"timestamp\", \"action\"])\n .limit(10)\n .to_list()\n)\n\nfor row in frame_rows:\n print(row[\"episode_index\"], row[\"frame_index\"], row[\"timestamp\"])\n"; -export const PyFrameworksLerobotLancedbImageDataset = "from lerobot_lancedb import LeRobotLanceDataset\n\ndataset = LeRobotLanceDataset(\n repo_id=\"your-org/your-lerobot-lance-images\",\n delta_timestamps={\n \"observation.images.front\": [-0.2, -0.1, 0.0],\n },\n return_uint8=True,\n)\n\nsample = dataset[0]\nprint(sample[\"observation.state\"].shape)\nprint(sample[\"action\"].shape)\n"; +export const PyFrameworksLerobotLoad = "from lerobot.datasets import LeRobotDataset\n\n# Hub dataset repo: storage_format in meta/info.json routes to the Lance reader\ndataset = LeRobotDataset(\"lance-format/pusht-lance\")\n\n# HF Storage Bucket, read in place, nothing downloaded\ndataset = LeRobotDataset(\"lance-format/lerobot-tests/pusht-lance\", repo_type=\"bucket\")\n\nsample = dataset[100]\nprint(sample[\"observation.state\"].shape)\nprint(sample[\"observation.image\"].shape)\n"; -export const PyFrameworksLerobotLancedbVideoDataset = "from lerobot_lancedb import LeRobotLanceVideoDataset\n\nvideo_dataset = LeRobotLanceVideoDataset(\n repo_id=\"lance-format/lerobot-pusht-lance\",\n delta_timestamps={\n \"observation.images.image\": [-0.2, -0.1, 0.0],\n },\n return_uint8=True,\n)\n\nvideo_sample = video_dataset[0]\nprint(video_sample[\"observation.images.image\"].shape)\n"; +export const PyFrameworksLerobotOpenLanceTables = "import lancedb\n\ndb = lancedb.connect(\"hf://datasets/lance-format/pusht-lance\")\nframes = db.open_table(\"frames\")\nvideos = db.open_table(\"videos\")\n\nprint(frames.count_rows(), videos.count_rows())\nprint(frames.schema)\n"; -export const PyFrameworksLerobotOpenLanceTables = "import lancedb\n\ndb = lancedb.connect(\"hf://datasets/lance-format/lerobot-pusht-lance/data\")\nframes = db.open_table(\"frames\")\nepisodes = db.open_table(\"episodes\")\nvideos = db.open_table(\"videos\")\n\nprint(len(frames), len(episodes), len(videos))\nprint(frames.schema)\n"; +export const PyFrameworksLerobotTrainReady = "import torch\n\ndataset = LeRobotDataset(\n \"lance-format/pusht-lance\",\n delta_timestamps={\"observation.image\": [-0.2, -0.1, 0.0]},\n return_uint8=True,\n)\nloader = torch.utils.data.DataLoader(dataset, batch_size=32, shuffle=True)\nbatch = next(iter(loader))\nprint(batch[\"observation.image\"].shape) # [32, 3, C, H, W]\n"; export const PyFrameworksLlamaindexAddReranker = "from lancedb.rerankers import ColbertReranker\n\nreranker = ColbertReranker()\nvector_store._add_reranker(reranker)\n"; diff --git a/docs/web/sql/sampling.mdx b/docs/web/sql/sampling.mdx index e45dd1980..0c190d4d5 100644 --- a/docs/web/sql/sampling.mdx +++ b/docs/web/sql/sampling.mdx @@ -97,5 +97,5 @@ would draw from are not all in the fragments yet. ## Sampling outside SQL {#sdk} For a training loop rather than a query, the SDKs read a table in a shuffled -order without going through SQL at all -- see [Training](/training), where a +order without going through SQL at all -- see [Training](/training/data-loading), where a permutation drives the data loader. diff --git a/docs/web/static/assets/images/indexing/hnsw_layered_graph.png b/docs/web/static/assets/images/indexing/hnsw_layered_graph.png new file mode 100644 index 0000000000000000000000000000000000000000..3cd835af291e1cc4bce0d939c0ca05782035c474 GIT binary patch literal 58243 zcmbrlby!s07dDKPqz>INba$6Bbc-O}-AGF}4xN(HQqm1lf^M6lCBI)BaB};1BA1 zS#1|MICLD??=!gc&xF9uI&&>K3pqI^I27O?WH{_+2yoAUE7&jbGo-(NHGpf9|E>*y zYli=xfd{T};Q!C_)*li7K5qfshyBO`zp!!s_ZOH-+;ccY;0^~DC&#n+f7j1|5#VzE zyU)qN@hs=xh)+*&aPT?*M&tq>LHO@_8a5>GgQ}O+0|!S5CnqVc{^9dM+w(ZRSmxhmsi>2ZwYxK3=B+jB-?pIzS!4nIhz z!S? zE816vo|JoDd6OUG(XU=b_!Wh=YM%46Y_{d${%M~Vv%L4sf8g;mJQp6hYP-FSdeB#B zu9$qRD6pHgZl5j3yEYiV+COd_x_tEYEoweGyF>S_gxvXk_UW5?teEtXyF4>!9i6YW zJQ$wmZZLZE**_we1S8yQK~v{zEeLK^LjOs91Kv_OyWwRFMJ*WplD+q%(tje(bG{c`1^o;guKF+1ZysCTzETq#{k^Y42;Kien%zcR`TMaV@zEf^ zV+W&K@WsqNzSkk9`cv`LasI2p8{+Bn%q?NREf>EnfxbX7f3W1C+UL06rf`D(kFBEj zCqLFdoc0hb_Qz9~mzM5R2NiY%GJgwT3$Y6}Jm>x6IkGEwekC?OJ9M!U>Jy{a1)jaR zy10jQwCH7n7i}+SU2kuPZ+r+&XZK>;voa1JoHK2!XAS&2v>Rqww)pq=g@)W7o5dU( zR(Tf%&pjTSD~8$)@0Go z@G*R~*fGG1|Kj3!a<(;XbpNt(eBJcdM1g|+NIEZ{NjKEbP!pOjmnFBloyB% z1Qi!#$&{>$S4W-(3dO!9NI`IVQSi7J=vS_@TeQ_$h`hnewB^NcaX+-&;qtIp+;nK0 z*h?{Vd0Z2n>zip=F&n#@q7*>zXTB!W-@o#c0%*tO#Y3iwShn!uuTa0Ec0~8~%1`#n zd&fQ=2Xn^sDp?q|wYHUQGhr_&R(8%p3DI;Gbq*zUGe)xcSHHE?l8A+=_X{|--xQYX zHvSC5B(Z2*cF$1C6q*JsMDU_EE#+h#bTZpbYU=szgA|`?&OSt)Td$+61H|2NJ6+jz zXj{?T>(G898Qh04->{FvFpSxw4h3Y&3+>hDoPi;JEE7tK6_-MMqcn5KwrGQ|`>n zOgz)fzoxMGIaJ%$#s+P_3YhdlBzrsIk;Ir$0hS3v2^#p9QRaM|wc2~`A41%oe>SVQ zMzkqmyv22BG`+U}96^;VM}G+QexhAYMhp`7~k5RA`az6<2O=c>Z* z*Iw^3Fl$y|2tPZ(_69w<3kZ80 z)%8*Mi@4%*Sq-Q2GB>3UEGxp^HL)^QBNBJHJeUW)sx=?NCwb-9y6il}3Pvag1&dFk z5q&R@Iv^^38e;EQs%XF6d*h9~Km5Az9QUudZcvH!h8djOoqqLFTA`peUCij(pKkPQ ziHWM3)@jtnIlUkgGE)&bmE7g|0OwcKRwrX7U^A<44RONz$`5Ne-o-tBEXBre@2m*); zg}4hogdsE?o9q4FRLL9JvrLZ_RB;P4ezpHSEk0;5WBTzW#S6v^?IKqFZ#-s#8GtEH;j2 z`9I!JTFEYT>qH9$LevZ61pQ~Wf2P?=pvu9Kd+p|~xw{|M&o1;37?KLTgvk7RyAKlV z7REcj(&il;iacA(T+u}J#hzT$%e7fWRb7B4QD9|8XAwe|g<&-DMNa%wC0k5?01i1$ zvWo?)`LO9UG8n@cChLBST=BVsh58{ryE&us@^bgBPnuyTaHz!bk>3EZ9W6D-VXQ^- zuT*_v)?E1dt`q`CJVVr+u|=<*K#G%Q%9SRV_qNH;N|e+aJ6XP{9BiG-%a_V~xq@70 z%Jg9Tt2AW{ruusXAs9hnm=**)u#>&QgZqkt(?k+BQ$jaD%A($vb80H0=75e?w;X*N z+8)U$GK158UB$y|hA8V1t8E#p?OilqU5hHbWYN&UYfbT4ey;gvR6s6R@!A8LfH*;a zpVCfg)m!()eovs5$W)EbEoy#q+}hTf$JXKg#Mf$q2bhJVFB&mlnxMmKyJ+_q@TD^v zl?G&pN(u@Ju$iE^F`L1SLw0ihlo41{5xtg?ky+NY1W`fJLk89pEj}vK+O1Z9X?yhR zx+GW7(qzIy9BF2&{dqKeM))4Y;!qwK^@$d%ee}I&0e5oRc41w#jk1;tj(?H;z*L>S z5VQFiePM7@nh+mZ86QfK&=Vs}TfdoKpR9v10)o=J$BfFw$MjrAcssqQ_c9v1@VS1D z=gS1UZGR6$aKD(=e4edX+-C;28(Y{L^$-=Vq7i%*B`r&j?HU*3v_q}^JT;iSJgUAM#fy)%-v1eDaNE});kJlccIqQ*aQ!_2 zm{LM`8naut6fSkK-{}K3VZWX4uTMLd%aZX2o06~so>FW{4omnG`7Bc3k?yo$U;Z}l zJK#>qY^dYakuWu#i$B#T>L6=lw=s!{%(T1OI{SS6aPvlCHUcI!YmVc@tthF(LZytL zPZonojK<6E<5C2l?#{a@slbWP`(h~?FZO2_bsgLACLZH40;IUaE$gdfdwk0-qUH@n zmdu1-(Aj)88GGL>d9SB*+H&XFBhYL(3sw#w&k6z*=I!V{;)@ z*)KLwT4_;EGH(COB+(m{Mbf$`NhTS79PJ~qKiroi(Kp5?n)yw(jCz;(uH1dpJac9x zttN|HN9FqHVYjh5bsb(-!p=E+7G(p7{?6SS@bSKq-Yi?sv%GSOeABQ^_dXpxf7f)} zv|{n}E{`>%YJcdEjUq)PoCetU=`cq~!Y6$3v&%)t#o;t=!0sN**ADr5nZU)zF@o?1 zphUyT==dxs^_H^8Zw`+vaPxi6-gG@4l}InT(O{WaFo83`osVYBx_s33Pm7|~8DeZ| zEZjEJ&{ei>-?EO-HgsYFsg*n`#z(D&9nZ7bU%SUR^$P)!3D*y&9s068mr|4Y5&QDNl0;%%A&0>t*Udzp+Wxm>Z2_yb{<7#y>TdOr<<(rH z!|&?(Uz0QA`uEHPiI!q1x>~t19funEOzuDKWB+w6Ozh`@)dQzdGp3(FV^!<~t^U5axGEhIs1 zVM%?M1B#|Zf`rNGZzv~+zfEE$3tY8F+wE2%xfCvxr^GgpB!98*Iw2QcP1Am_>1|OH zh$}OWB)A&w&mOu`2##7}Wp{A<({aOpqmzGs;c4K%LCa>A*A*HT;H-*U&vrpud@CgF z*w-=i*5S%cY1^euW1p85&;z(L6qmvEA0K}#L}S#`AT(_y>)QR<9Dv0gh~@U>?s?@( zkV0JLOd&j*Q9wibG%ECnBDgRq#9D2ZM^GLe9XN#D>5MBovg>A76y|2GaNO@*sixe2 z%cre>2)V+VA&v>PB56-hcifj#z2zcXiM`6?Zl2$E7qtz?sYF5_@2>t~ztqjhXS|UV z7ib1V1O!3H+EB>Uw>OoWHGH3({TZKTkQAr9l16&iW>-(|@;3%qRoHqd*#@0?{S8EZ zGHOQBhwcv1j%E|o+ilrA`d(Z$`KOE@^Db7$-Gvm>?$QlQVB*>x*{?sMKkXNI)RtXY zSdh#63J`?fg7@6299PA>kD7N5#&RXx=gm_>SuB6`Ml%DUB79sN(QEhP75kT>=Wli? zVS$q@@>*oI&6g6*vCqGGgx$o9pDWWG)IXpu`f*qnEy{%tKUi1_Vb3fla?pg|NOp~M zf5bt)wqKf-W#ITmYtK58wwN-iJRdR7n86#o7iuF7Wttl^Iw z?gw*YK%hqG{-$ZN(-gn!!NpK1{)f-_ZcLhPMhMV}sN_4w<^Z--k# zy~k&gSgJ#biL5sg{&J)nU1$W*;?zC%a7nS_ooda{Z_5`Kj<*nB6%31JxD6pJ_QPch zOJS>U4tgvJqHejtC_FSxaK7xE>;CeGA1y{&`SbnBfI}W=dUqz$`f{#pvOw1mpV){x zosf8jL{ra6s{akMxEh&kKL!U&)JcaAkRjTS=Shh#*M7f5QsM2&$&Na3z4$V${FztS zOUPJ8nf9Rnwwx^Z@AGTw zR-S!jb`@KtUT&&BE&KX)#=P#w1mhPrqL%I(dQ?kdPIOos3~Bz5eLUVylgT^cVR0o) zYZ87D?w8RN)_lg23v^NPiwPyxx*Uw$n))D#l9#N4d3;V+=Dp5{BY^J?D#9e^3&DsR zlT&BI<_bo9Oo@H<_(5O-i>>W^;;RZWhk`9?zLKHqkyo27PqJtywT3M^|Q*Snb z4#)JlsP;8H!?*q6qw9f0dI?*5`}&t+*OW_QzPELmf-ZCiHoqdalSyKzrK3=~5&{Q) zL41k~peBhDxHi^%`-JrZ<_g!KdZwPqa7%AL9x~5+Pp8OtB4Ek;n>C`t8oc}w{Gue* z7)G66jOj5Vx^JOYXVKw${xZM5$}1s*8(aS*Vv!L=4&^4IE`EDutb0j+_*%E?MYba1 zD4f5+d$*YG_tN^qZ1+KJXTwOdHFesW9^24&77K*6C8lZ(KGF*s!*cUW;npOtKF^Ir z)k{x(%*h??xY^DCBd6DQ?@gCVyrrLcnfC`cW@da2ON3?IEMEr6`5_Y%A&hbmKNkZO>0Vt=g8&0R|bY!O2yj2{Cf@k_b9ygU(( zBIad6A(6y9vTiB>e-P0Clc#_s%eB*PYhQ2u`lbnOG33c&WeSpS9x(}iJaF)QFh4kZ z{Cp^Q3g6Vc^ygL{7t3ujl0F2AR%e&Tntk^RzBJAZ)YC1Bi3G)w>_%@%xXdOYIVhKa zrbJbpet+!jE$2<+RqfhVk)Q8lSDIf=xkP+MyRYc``pJas`-d90{TZX&bumOt2g`Fy zRX<=U0z_~@VW_46cmm$aR{3u7{&ab%Sa+e>We4)ZHEOF@>V+HRtHLzb|*UjvhVZB}Q!%){s0e zvrZlNCI=i}FX$G|8p z62uo>VbrKdAc2F8ZiJ#xP`#Ykk!O!iZeF8H0p6&)a5^Q`qKh7B^95s;I@ROx#sKZc zXf!sS+-djA@x?SGll*!fI=kg8#)jWh5mgo_j1SCE7c%?}^T#XiZxRdJ@Ux0}(m5}& z$zPk~&Kh{LYFVAEe23Kf-28FQHdr2K0;?Ikx!9j6M~^hN8I8lpNw*!HqB<>;9Uu5C zK%&C%I)5eFQViUVoWjGxf0WgGOgb8cYY#z*f9XpbuzTEoZBL(7&boL#wd%_jRYM!R z%Z(>EQ=tB_+}|IJa(%nkLlOBfz$&WvMk<9q)NI z!Vd%KfQZaZqBKPD##ocWqgK<qZiJI&V6HxwLJ&K5$DIU@`-(7L-n zAM@NDPK#c8^IsyWQX_Iaaew?(5SZf$0ARs)H|32h#Cxa_ol=m(u7qbsnYs9Ap*-x( zo7l7n#T#GXvsk0m$G$9Wdt8`g@eEHiWi^we7X@3$d~9MwRGtdWpQu4c1$V!OG*PWI zUfJ8BL=&@*DA7D)$abTf5=FO8!*M^GAipzoJZLzj-qfJ;Ba6i}<;L--1(J;UGVR)+ zq4`$NGe8Ku3V;x{0^N|`y|Q1Z8+$g_)+dyI9kEBP`Az-1d~lA_5N2?8Q4ErYg2b9p zTPHn#x;aCZlN<{8D;@{3P11MdLl}A5-rPQ7+TmA+X`D|)%cIMm*GQd zmp7%}5P0|kLww)$GoFg=shs(G+mw+k(Z#HRnCeo_%%Lg< zV9oBkV_@BC6RBd+;0a4h!zqim&-`?;(bjDG;dbSa-mCriDj{T5#``5edhUI9La;aS ztTYd6Sx7V}Zvr}d^{02$pkH9>a?h&qsKVWQ=ewu(M*U=i=`rfQU7G!&X+>S3KWU!=*~#zIbOK2yB~jS+>#LxQWhyprE1S-3s8c_8!=7*>Tzj5v}&s{p~k zB$+lbGRkyqEq@0od^=xl`mtQUg^xwUi9dteGA7~K6vOzyGB-}MEfIX*@`S*I)5A?u zj&XB1-;qm_`fC(Ut#0nGJ*=bS=c7@Uc2jE_B%)mHPK)K^or9m{wI#Ulu)l=BPvo;T zAh@R;3QpL!#L$)HGaF+LxK^doV5f18tTwPaxfq}S$_{h+;lyfRW!bMBL%@B_!_5OV6B!Ea=!*CLmBhN$` z(*MzFq+-pAFR!%-n3u8BnsKL5;K4%&#i&R=1 zIfXC6-oFdAxuQCAF%NFSQwg+-w&L8fj_waaF21L0tgwM>PK4;ux65KDoMCm&B&YZJr1JM?l;w+Spr$2;h6l8JD)J?UFw? zy_0&-g9Zk-_xi~Dd+nDu9sme3hA)u^cX~^HxS=5gI z1>(+?lg3R~|2`@1LV>`Dilnz@)NJh3y{f0HXUXHCVk+MK0^7og9c3?V)|D0QRCNO% z_tk{u`v+HoH+)5eqiI#Y{mDx=PMJiMm%{tHj2YK=9SpN>hGGp8nKJNb*}Q-V1N|Yj z+2!u?@Ujb?J!G+LADSO-L4!v`V`hV*7jo3`^mvk=x5nOa{|Ei%CX^w}s*tB6StMuH z)S>CfilvUwO#4lBZR9i%iaFSvh9nOeEWSx58&k<^ok?91crBDAHgv{nb#x$zZfju78TW zvh6Zm^m5MB80`5gnm8xwPu2j9$KE#?_fBxWA+6;BMC zmqNF3Gd;?>AO(qQ{>`+L(36 zTDv1a)0hvLPJts)K!N9D@9GquS?xk!mRBKwQScdKg}2~ipA7wv3ot)Zu6wv(TZtKH zdN9XXg2qXB{i5m^p4vpjyp$gAeeRE-QIEvx8A=CPrq`xe&$Hfq4-TtmzzLS~`N*w_ z=QVoNQ-2uUAnd5Q}=Ornx7x&>UX0Lg-LS1vE&(fj7vvbH4y}^CDQy52(QU+gW zb;yX#9{LQoJvLYU$f9G1JuL3QIRL6CLa;{i}cvLKi;q^|9JZ1b)vb6=X z_??m*ECCcUeE0Ua^JPoc14;0v^J&m7?^YugRaC~&9-e(W7`Lr`p4LqvBGUC`&Q5yF z^JC$87AEXN2-L1=pTULB!~y`IjS=F^R0s@xs;8-8Gk8fi0K+*;E8A_jErwBgc(h5m zh-|xXC8F6M^Q2CEI%Os1C|&OzvwmC*8XX>4x67IZqMRm;O{4TYT1~a>it06Cj(ZW@ zvrjK}%Y;84m0@Lc0JL)?6b(JtYFx(Sj*4R?c(<*XB^mcg_*P(a)Iy4}K?A^G&&_j< zu~h8Eu@T!Yv1=r7Ra%lK&UUT=PQx7lujGI*=)jegZ^h1!^yws@#-QM8EDE1<~h zT&efdzEWf*by%HmN8l^1J$3pBVZ$Vr@vlbawO=n#oS3EghNP#u)*TGUC6A*8@In;o z;Am#Clas9A+KQ;Rq0Fgzp2(e3P-BxS;0Vp#wPbh30NQV39nkaU#oXrX3Ne!{z4UY=QFkx=ISaa zT`bF|$BJRI0dclUt07b-zUbQy3yHQ;Uc6Sd&JY!|ucc2NAxuHru+UPIK5)Hkm*xej zh?ADPY^Js7tx2;ovZ>$m;S*E}9e19QE+=e+lIOEJ$f?4$f%4LghE2<;$v-8H9Jiju z014ZWL&w8q+(}8YwY_aUjy<3=7s%+(%D54u^#LRdtj~?pwlpG1`wLxfmCSN{plceT z^d*JZeS9~($ZT-wvQ2OXG5p6n-*sXFK7{G#RdpDSy%Q#vKjWjU<^ep+ksMZY3UND+ zNUu=u)d|+RsUJPq!EK>X?Y5@U3ggYdbmX$N=F%0RHBb4eIR81^BC_y{-G*%KnSR=i zrVd;ig(zLm@;4FaiY1GUZd0~VM(b_27NGzk9`+a8M7ufZ>6ngzDrtQz*Y93*dXl4Dwm zMb`y)BT3i!#XTRBAz9^S3po1IhounN;%f|!(sDz^8wEbC?8Pt zl#f4uL0Yww<^6NT`?xJ`83TRfi(FzEKEPulFfx{Lugw(p2wUK$LCis5APOi(%8PWW zEIY~zL2~CI<2kYx>81I8);5EQ@QUhrow#vk+I=8DYhXeeHm-#8ghr7QO?G*V^ zs&nB}YJQT}a{d?=^L`iW>ns(E=_rpVj?-w;qu+V0=dc{1^G1Xm=^0cuJOaI)zrD7Y zwg)Nq`Gh5ow6ch_lxZvog8T9ptF2%RN;)P9Ux???gaSJzJ~7|%S0YrRQ`@+UATv0< za}R*P5NZbZRg~H$dY5X2`>j)VJ+=ZS<`oaJFaD7ho>r5o_;;Idq`pW`6VX%-_Yl!L z<@|?HnYZqR)YK+SNM#%-UmaJ{>qaYhggx4agoK2DSRNjT{vpz@y55nhJ4w5V5wQ-^ zm0wE0t}naB!XjkfOI7+TTZ{tk9t+4Zwp*#U1$ZaMXGamt6)54^bML=O)0jzWyeIJ7 z2&cDOY_JD^qNulQ>eoK8S_j)?HdUPx(~$pKpCKVO>02)7jdf^9QP#7_P%*&fiZsqG zp%L;Cq5nhZt=)7`NYrlP!`;=Q#7j|JJx5smm+Nz2!ZWBB)t)=vONS!I zwFqfp&-l?{QKJYuV z8o;-H)BhO|2hYNzwTjC8dW?fW9RZsw&u~t^z?o$L?tMO3)()Ui7(WBb+IcId18}9o zC+l)|181U_Paq7z*YL<9(ZQ}oNr%f{vWzPIO9Gt|K}))|Jr7t5GYPcUly_eZ*){9;H>vh*m$Ffnz6;P|^#6~egGwO{rNk&6( zVhEdGgp{Wy&7X5xw>TRtIOu$?!E<@L{`nh?2~eFoM>x%a;?H=aqyu3O5<5`x+Db8W z_ynj6LwNA>mkar^V#G0eOJ7bUMuvm{DN3Tv5Y2hB7%#r0vD;byV*e_&3TFp|8xHt; zxp*E*dra+arMj|6Z$Bw1^dQ<#%32as_Da$CTm{iYSqTgXYqJhZ}Ee#rY{VrHj2{)uI zN#7Yx!x>Jf`3d#<2wp*WDq)rQ{t(ZN>V0N3aY@Q8?8Ili)53L?y(g=s$uGr=)B7Rn zBqxU!pY&0*oHMPV5OBjba*M^r7C+L5dt+q*XxoBdRCfNn+L~nEj_)fiwby%Uwd+V= zH{K$_ND{KsiU$}P#Ba}j#n%F!M+lp1XLMmn&?Qn(Q+54~$Z<-?y*WdjWcoHN?c1c* zJR|~h1tHI}c`%>dHAR0HbQdzFUmRHw#_9BeJX7d3(~|bn zvQ?^@`oiUp4u}ImN@}Y`-XXL|XsD{`7}^ z9e#&TEP3n23mh2j0#q=YlN&&X3I|l^$nPdn+HpfhUix24v>dnJ9RQp}jgq7{AeW`J ztTYB@C}EPI)F&8YYvSCAh6wJRY4xyTDhF6Zvzq(wSkp>EnJ@Az&UeQf?B;8XKFxRd zcZfcmPr3u-gQ_D_RxLRsPV;yy&syiLL8Hv|uEzltKa-cQ?%y|ESN&YGgfUP66fC2n zqQWRQO~~!5@9kuE!>Iq`+04QMv4{&S5sRbAc^fAsz3Iv-;cFTn4k7;&$@Z<^Vl;~^ zsEeUcE@$ri_hfKsnu+DVv9i^f%tb{-!BX7&;vtx)lR&;u%We5HMA0(ofT2jLuyHB_ zG|#@G$D-FX)_ybMxKKMPMxq$A*yz{@q!*%kn?R!VSJEV|?(ShDHe6}rmq*Ja5X=UL zWgAU>w@>>14;Q)WGJ?RI%#aGA3AL+?#Iu2z)zRQ2pGKdXfS2GdiikVtQz1K;=HHY) zsx#qjSiuUAHki&|inm=xMG4B7KJ3IDx-+nH$#<~SY&^RUHKX$e_S)`np*)V zHf0WA(bxgv2ftT5viQ46^|V&$>FHg_0^0WBnRKdfJyTdbU!0C!q7regtuaZf4re%g zD=GGmecJpL`-HGXp{VKxSpe+jPNf3?E5LAjj>TE3S^2_=#}}0t zHiX?m9b;33??tI0>u|^>nCscw)s(ybL+&v@v`8^~M`THHZHeV4G`gZH>CI1>n6k z6c4*Hms4sg^Ompf=HqVca)9Vako`6M#dCNQv-bNf_Qju>!V-sR`7*KiNs_N&8V^yY zz{JGl^MAa5llANV=FEMgI~)zfr4urPgkaCB4aA66e+313y%6z|pOEkgteVKc0XwO{ zt4!EjRLs}Bz^T%!W`QJq|2mWM$wiY1w$efY*8sfani{Kds=K8fu_7&e zu)LyayYY`O=j<@hy8$4Uvm6yUi;7@E2Rr8(`N!jZt)B=1^+ql^=z8%t@(#>#v(gUt*D%!GwX z6puH2^CJwC`N|qab^6QX?=jdXoF_19JB*w|EqTgmfjg!~feqP&bUp$f$-Zg(Fr3P{ zC58$9nqWOyI1l8ErqR(lUx8)hkBe^(!Tkv+GXw{4hyC@6W}(-q zs`=7#!ziloJ3ljP0l)OMsthCrP#YN+Yb|4MV?k8(FmVASmnvY@jei#bi^K13M*R(r zCP8^N=!0S>-w|e}r{5i^VL{XxV2`u1vUbu+3*Lt^uxh1ArP>UjsOnuRZc_o=Kq;r% zQZDF}$Z^M0yXg6tgflBn9-=x3#)sO?2*K;Ht{~Dd+XBqi<&3VQwwjt+vx?N;eS;bT zME^~m-~9aiDR(>}#a`+N62J$9q_9o_6Oa@JQ3{Pk2m|RYCa1;TD`0*9B*y7|Y1i_2 zyDu@;0m|bjR7^7gPyn?FBCw<~@U3Q{WE@Dh=&Hmx^vW1YD5?UJMJg`=hPyL3GO8a< z{1LZD9n1xeD5|ZURL&C7{=4A2mr|TtI%zmuXGYMgM#`W~D*zus- ztReyZY6b}OGN0ms0fiV?c9`Cfq(;9MpUd{}Ume24S8BFGQzeDX^buxxwg67vWj}Rn zKNYnkYB6OYs3-rCI%M}{Gzd_jVKQNNEz|rc_rF>VD+gm~8xtr3D)c{%2J`?b_K159 zY;X*)Yk9B!Nd?`c!k|q@J0*kx-lo4yr(WKP3j+O&yCeLCsfG8Y=iNIAY3M{Mk99)1 zcCEAV5y1f>=V^)fjKpaTfo^nS z|EQ?(0W^dZQPJDm8~6eg)lMsSJZ(Y0`zE0BuizYxm4~>Q$0&JP{DcC&1vcMo3vi~5 zJK6pQY@GiDK@|^}icYdHGS2_b4<>MaaKZ_}@>i$y($XlZK2NH*&R|KlztV_H<+V+Q zrHOxM+3>XFI;k`>HKqPfZ_xrk+N$D;V0js&hY*G=Mzz8az(Y5~_9j%3^B@RzNJPlU z$lQUl0p2-I9?H)wQClE&RwaY!5-bk^I9OI!E8dQOg~h&mwHEv`8K$Z7mxqg%v0}Hy zgK&UmQO$D2f5M`c21aKfkGKIi3exp};3s<0+Vi`)Vds*H+8Mvw2cYL}>d;AsGY-=N zs`X+ob$z3(%p3v@#N#4Xx5u`Wc=CM?v=0wARZL)y_G?N7QR!JnzPzJI? zI&{^0Qpta|0+1ilGioeqN$a(Axn3^TZs4qJQ(jPjB@O>ODfSCIy7e}nOhy1T0Ib41 z0O~->fKc5`B0so40?hZb;H=OUt7A`uYK0X(-j* zXgCf%&r4Kb!GI~{@_+PcxjSm%4FoJri~C_s_TzaG(87b;nJe+}0LIX~NDTo|kpR{} zn@G_43#(RD4$Rg}A2Vc&`3jjCU_)@j5`Mz;ptiIh?T7;)n6vz~kX0yZWEkKG8K4Ph zoB(EfT0D*$?v6V;fY<-pR7nlk-pomn^Vw;^vXL3%nOx2iqH%X9VPW@QdQ931%_^eeW*k+5K-6!im5U zYipgsmw?v5m;r;nOb{rVRE0SeGeBLbqE$#vg6WbCh{JL;ixsx?Pe###ZhJ{(uoDgF zOikBjH9)A}-`!=nDnU`LhuM&V3knn7tqqocwn`gx_PZ#%Avrl2wk8Nv2#-sPmlm*| zur&+PgW!QFL!i!p>kHXMFISgRPHHiPPP~Dg37C^*LIP@A;jm^b4D4Thv5kT*+YDOT zP%1(`yHr-gb`jE0U;_tr=$xrs+Cc@J))O=>zY8;_0NYdZv;;&Cuu~_AL=70$2-wQW zSU3T0cuhZwDk9L&Ff%hl2T19^gT!uNXL!FsFyu=NQRjt0D3)2C(&(IkgkW7iXW36n z$^iHL-?{y(GQ2kG0Bc~vJ*h;#0wVx|>o}g|5dfkhNY|Ir01US^fDKF{QvEZm1sB=9 zz0&4mxR6arm{9@Bf3*N-!0o&^X7J}R?cdC8%BJl>LV zdPc@4J`E_g@4c{)&>(Dvv@`=bl!e>izjj7a*%qUH0GJD!37c+%B3n8H_Zg}sKnN@e zN(DB`s(|ShmumqPC+`EDN)~B4D6c6xK=`OBAEvIwMs-RIH9-Mj(= zM@0;xfy26~T#l9m7u&oW0Xn0|fnh3|1JOj(u?_BV-&$&&b0-*L* z5XSl7li#o@Bmb(uy=8mwyzx;PA3gTR*&ID?0<^OQz{0vrhJBOHJeMI^1W$Soz6}sD zf3YiqTT%17tI$^e+)>6YVTMb$=fRx@{V!+sQ*OU?_f;{zKbWiLV0+Q)y_vUQ;E`h} zyvkXSG)oaRdofGiKTA}07S-No)Jk45q%C9g>G#0_Y28&x_bkcotfszzYAHr>oHalU zdrslQab3%1&^iZ@OkIpm2IvTH(P-Ft`dgD`2X|I2a75?Hhv>Th+_3oizVdDJyT9=b zZ}NG?-eL%AF^H_}Bll*(2w2KKwjA0aJ@aJ|dq&``zj-HYCY%jfZ5;F0Ean*A5uBIw z2Lusna9^!Qg5slZNjOqY>X)-o&C|5^(v=R;uxhiF&eCfcdFZeR*#(lZFi7S@Tv>TmRoJO{VirB?AZ1m zwVwS1xy+cYd8JiCB8T8aKJLPJS?x3G!ExLEO8Myq zuz`^8ul7;ia_;QCLU3zKs)^SaG`+E_NaCujLjGa89ZFz;atQRlpeV6<=iw8c7(K}) z(#;ceTuUvs`?iQaUjKp->RW*RpdSxfmS63~^*`)i$krs%*rWp%1)E{nAdAHeks1L29j z-^~`EaaV|6@MGy#?Wg?FQ%9gz$;KOKsW_as%&rIOOXENz*!G+EN!9XD8(LWJ>y>NYMI`57qaoiMjbu-8u zZR>B&wsk!`jQ2;vo-Qq)9{e}&HqE%O+zGwEwb(7qIeD@|!#|~o`F?8yLSyiU&rNBt zct>0gL2c`WdlNFbz**?$0D!NezOGg2R2%`z?Hozd)gW{6VUpAMN%wABe_222z-G@h2=9ruk+nE zHtQLy_dtgP-^k;`>eKS$I>jTnDHWX)_e=S;nAoQ7;lT;Dg+udJ@>=#yq~Sf)!MC^< zZ-k#d1zHMpIv0|0fFqt0U`E?QaAR*r*McoE$hm1~Zl;RF%vY~_`RxFEb{R}@|GoWg z`8e#GGmw^=lYmb~?k^iV$nH7)FKe?yS%?o_7-h!$TX=S&NgSe2^irAe#KU}4J?07* zE|^vV$W5=B-zX!b%pLnb-Cd48-H$dnuC_a8=Ycw;wKa>O$p8kl=(peK2Q*EtI=;GJ ze`yc2WEz8&EHG8YK#7B#>_9LyWq6OlX4yRe41|t(<$vtGiXIdetqf)gjd+8OJ8{1- z+m8PyUCld;#qtXR&6?t4H3UPHPzvXCG5*f$=^m1)NTc zP2P^Zucbk@I6=}VoF8a#ER--UFy(5qlC(9^R;_C*vQ|30hlPHuhL3&oo|s8h)KW7Q zx^F2A8?NTGo*{gEJh_lXUtKoUFyc!1`mwsSpg`)V27()St788BHgXki{LiOKpB@0; zTL!&&4G9=xYZ-=>_uicALH8J;^M6a1+{N_LSR;lHdzzg+QFfMq0l5!?ORtSja-*WH@y#EUE*;kopx$wQ(cGzd+mdBcYiy-jr^#MupurW1VjiVKCY+!i=#t6njZ6O1PF zP{g%QlXY%cQQGk$|dK0#n718aHVC@89>|P zWw`n9KQ4f`_ENz?SM<5e^5BQlIBCwMpIXku*cNB>MfT&Hb*!Hg8Wb$P*matf2@)B1 zr@kv)*8VgQ%0PaRJ@{zfDuS?&gs23xSDt(k9|I9nhD^7_IiaxVwz%8NzWe~|HT>HI z-07i)5hM5nw0B$rC9%IL#yAUV+CugBwM(~+viX?@STWK1m|SjdoVzJ9t)9n%+#~w! zAbIhV_Y6fRYq_v7tCDpFmykU=ea5n@YOFpVxA`xbnZiY)L=myA(N|Bc%bq)#;LH*< zIP`c56he7!pphTk#HPBa2#6I4C~D1^0zJMKCtq@#wgH0mA>c`0^4f$DDuUHGIk|kr zPo9neit_>hXi4PESLnCc0af765V@Uks+JF272*_pAI~GNTe+MliA9mP8}pUaUutPx zhi5Ov*BLrkS9!$J1@U$-4}myU<=r-+bm&$NUkZY?1f7M90V-EpUC}tcvht!Oz_-;+ zF6?SH>MX(ARndxlb-fl`mCrIu2>$c&vFpC#QEk5J#rMN(UU*bEsLKk>r(G?%TmmJU zka}XJ(9s?vRXj*$bVKOCJLQ@}Tl(f^3*yl#aBMy8 zH7bbD!E$3Y3mB{gGU3WYpff4U@Afz7mCK@iBdlq)%S2};Ep}rgcmPfu2tMaQIUieA zfK2fKNPQZB@CDH4RG=t&1d&*STitKtF+0yf_qfHCo`ZYC zuOGJbeq>wU3SG-l!II|MR&zemV<5-KNXoph3*ytC*hP5`p;5s%2|efNK{qX*vW&-B_u)PQ93`EQF#LdD9F0%5j$Q8#;WK5p=`GA4@`bU)gRt1 z=0z+1kqlxVWTd1GuLAx39atk9uOIZD6lqAU_4PAnrso}O8XL_sAZSRCBOd}|BtoMIoGRto7KSILwi^R)bqr% zG!-9wC~o-tWDqT-<6M0=IoUPvA2O(qf822fj>&LrHS*9MPE`xej8%PSitjaBP;Mlz zwqNv^yNRiDyY%C0tirw?vOFEdc~~R~`WTH7^Z4Q1b17yuoB5JiGcq9-<*j(fpLHp{ z>U%5-e6EX&LbRuo(|*TPx?cv!OXN56(8WKC39Vb5{5Fyo=)^O&K%-4)8_+)qgU%4e z&#Gg6huHv<*H=Rds0|Jm9$)c?c)EmVah$>G0j`8!$7d2-h!BvfnXmI7_d6bK2^roK zk;uQ-&Ihv)0N{<`br%675801;X(24aE;-t+(FHSWp6=(aFABCKax@aZ3<1gb-7?cg z^s{B|<4xy`2y)-fk&R`NBj53kw(5Y`l^7jPlm?3Cg3iZB>;I3aw~UIbX}X3ZSONqK z?(XjH4hawvB)GcF})P=;Xd&A}V;=kFIO&*`W56WWh% z7wu1um!8({g%fk(sO?d!qsuIss@v7bA+JN*?W!hI4Scg-44UVwrjm!{c|zor!gcQjjdJhxWf1UpmNII$1Lab-?52|6^;GjR?p0MRM^{gD38XZZR;==@@R2ujzLeQL6{t4x z6@)!3sc*MeXyaOK*}M) zWO=OQ--;uqxU&}7l?PijQ`s<+KXpxUC(@+Vg?&`srT7F1jJU5o_4NrU;-0#(P@tBC zWdUZneQFw*qfF z!FH#0`;A+>F+{{J6K*PE0I`wKeVt4%K;{|FAeXC0GS@jB)nKF17gx+bWcJv~V#zB6-fUz1N3!@i(Mp-+veF4@kvoWE4I`7X-zbzVhv zV%*qWR5-cZ3^UWs)R^n>E>=aYR&Btt?b=dH3 z@MEVUGa>G**2IjMHgD}WIzIGJe`hOZZQ&GWr6oS5269Yw*+#48S36CHq5)??S>HHt z|7u2RZ5*>;j$C76Dk|ziPyEb!R_9X_(azz`pd;4K*8Bi=`FK&UJDcCRIf82nMnlR? zji!dc#sEX2cMOIxx7elJ4e4bmnbnJo$5lf{XRYx&JmumIMz+|7pK@P{h>VV2R)%{d zBk|tpQ}nP)h)ko z-Vt9~<%Tg@wyNP`qn7ZLd9m={kJVIiH}5eq-0y9@6Cb z1^NouHLdBpjMODzJ#2R|sr|?~8lM{y8$VSE#X{+W_1qfIP$HD?cJtVLq$lq_DrQ9M zxYE4-5T<7Dy{7kMf=39OuaSuLDZle20>|hyQs0p-4uUtM=_M z$L;0pWj32r)bpD}4*pB{_z#wN1w)wCe74jsv!F=G4EVB4^WL2&wc}yjZ?aILGbgj0 z_FY1Yuy@^oT@+?AE}}o}O1eb%U^({`ll9W}=5(X@M{a%15nS`4D!Hlv4Yp(ae5*tj zU1|)dsxP5@?7>O`QlLMh1t*6WasQY+yiJyK-F%dSnoHf&pW?7jo6nm7IzbXkdx`=` zJuZ*GXeu9}GCz@Pf0TSRw$T3k;L)Kjvt?{1HWT_#7^eT3;SX1r9$k{^wfQpq==F~4 zeA4%1!ey4t0o3(lYlc9sNy=rVeLeUkoRlN?jS%D<`hCy68yA#ijm(mY>5b$uQ4N&^ zM?&U@Manp!>=U!O65)!6Umxy&@pfDMtYr%4v3+Ar>Pca^e8Nk_$dz)zTEZ+qLLwPIVu(#`_|>n`3~{uLRL_z@wNlpbGnW|&?M*9 zIr_suPld;grLR0g%!Fa#02}dF?QbMwEMq)9gdiSA-u=b5`M{WuTjVzu8=a_CNNY4xZgxi?l6fsGC+Fg|UsqS%*LOpU zV%Cq?PexCpd78}4Ljn$8bMsM0+A)#}Z9fG+pUGnh)w=J=YQGO?w&i|!zG=4x=aTTg zFtqi^?D(Wpm_OcEr!u3|;L7!#4%Fk=sw6`8(%LT4PyD?bWqeXtyslKd&|&h-Fv73I z*o1H}Ybw(JYLG?X-wlF~InSq!Z~CRe0s>i(rt{Vovb;j}C74;ng--v@wLf1e9A)5b1LEzc zN*uWqwqhFdG3OK&o-4>km;zorX-DstuWFvP$H8}9PD8*@(N)s3n;bRRLW7bbB+!~j zKh^V+u0ZP|6K|5&7)JgFhqEN~?sUr&O1SPl&S+x_hIWs^Kv;876FRw89w(s_OO$1p z5phfOyGS|z<)iECf?~&i(Q1DAw4Edy21{^pzYRM0QU$UHKHys-nx67!zs*EsKIjZ= zggMaX!`0*)5M|f8c^k46ApWELCvdDV0moYJq1maAyxCs>kq05QG3UAHdzjoumfS~x z6Sd&L4pxO#WBjMWF4s)(T!qfgdZFNxX>jUV4ZeW8^Z2S8Sm5YNdTb9T6PrY}Q^R4c zCL08?tIzdJ_r|N`74~a$~+I*)5sQ7jw_<3 zoZp9nR%tBo=f5x-e6HwYwTfzB{`S5>e>BtLTJTtYA%|L;ckWr&g9bgQJ`$Iio+X!>m=-(IWWu;1ziNOli_ z=MP+Z`*cpST%`euZj7`C){;+UXXW=!f4{w?VNy6M3bNI7qgS2suU@{PGTU6@;A(O6 zH{li!6t|t?dz53Z8#fp=Nb!yXx*^y<(`NLX=Y!&;D_E%8I8eMd4CW ze>*|S`O*Jd(&nj`U)s&Ut)|u9;%8k3pYfh@5_v40RZ#C$bu%RzEQe|B{C)uS!(}Kz zsvx!Hk>*|FcL{U7I}}bfjB~azGRcb`e#u_l`oH5#;t^HJXOn%yMLo?+<&$YhdKsWZ z(p_-@D`D{NJ&3sxnM*86nQxri9dASkPjUx{o$&*IG>?5X2DUuvXbg;H$Rc(0ySJ5Yf=$FmeXQ z7RTx)oruLvZRk%^YyJt3+jPHi1{?L-Hk`%XJ@22w%~Pcl?!Pj$iJckrBK1}pRCXVF zoJ2ouhJa&_-~2{s<(2wf-;(or1WRvFi=UK={z$u_46l%3;-N6%p(xo?7953ggUT<5 z;5!#Ktt>@}Hg$Jcyoho%(GTP|s@9MFTt|BSn783cmxxYZ_3<2r?e6dHx?uv81SaW9B3gESt7*#nu2Qk&byvAz z0Yy@a+r={R!+za5-JEScF4qY;3OP*a37Op-4jUCzy5NR1+lc78z~0dx`B$>#U*9N& zC_b!XwyUD64bh-zBRBV8nzIb3-CB)ha9d7MMAZkt?|dKXCU>mW&uO*iGPK5%0@B5P z+rR)alv1+17bEIiH zF^U+I%WOzQoW)v`&n+_ke?k@gt2c3Pic{2t)~o`}W!Wj;Qb94g_lZk9A}7+E*I)4e(V-jG z5NfPED-~1)P72QYu?CZdBG(}}wi~=Lat6rhKNGfV@6U)nW7OP=T|DT~U%vaLv?Nr* z{A8DpjCi|U-%T^@6ymH)*NL7$=fq|;_2NfPv22OI9HMY~rD5C|na;ucH?i`mOq$n~ z<_p|x8BOxXwGbOQisH<8I4ko3v4X@&z^0w*&9l6Q5|jPUOQTYvW^DvxpWNYUR)Xdx z|9ax%47O~evD-ye+!^X?DSf|SdE&P36?1+wz6Wt9v9@u6Vd`w=s%;@Ks!Zoi|1I0E zv|k*8N9b-~x`1%^@W$)q=7?7NPUd!TIaAzn!xtxM7$Q@*kg>Pa%O;*mF83MCt}C1Q zR9h$AkHB$zS=~I?iLFBGyRgjvYgX4TX9`V0vJ8i!?X&wjnrLh}Ps#v=*}z(}v67>% z-&Nr2um@&(Rungu*O*)x>(g&5Y7F0?&U{hvZoAnpsaOCfES)EVk+@+PR!NHqVj=}h zIn1P&x*XBS3}7D+p}wk#d0T1Pd7;*HZPg$w)tZ85Tc>vBN2y=cBWv;tAg+ z6Z_*cxUbmOlUTtVAT+BUx_<3sIMwMS6BojdBhU-PVQ;uP#V0}tZ2D`+mhC;Kt&?^B zM|ItbOU02mxfFZYy${891KZm~Zh?R?FYnDvQg!kw9<%6zk*78kVqH#_M&g%u$(^2} z_jupF(XEm>X1z>uRy9R$`Uo7nZtd}mvQ1)XKO%wdBvyK?!w8|kvKivE|4Hel`*=xb z7A&PP>zsCyx#~Z{=cK5AxM_{!aRPSqsvu;}GS#Sn_LqnD`U;ODb9DVibkR(qK=#+> zT>A;clh&_W(wOWx~Eb@2Rq9w=vw~TZY*?D5)4t#qa z<5z#TL*@x4s2{fJRtk*1>tXcNO?Yq13Q+?vIP6DVg;4V8wR9|pBQjO5R7G~=Fa{EU zC-BWN?n{6^#dlglq0r(So8!rd0PhN0WVTcdEmYSvO@tizGtIwQTu)L*>}BJnxcAPX zUmOYUuuC|CmX?GyoREej8DN zwfDHOs*nO*yz95=6g|$&k4>stQZyoj_DNqY@#3S3WYzgFf>r~nCa3mU9a$1RZ<<%@ zARd!639^i>Y-xo0F8nu=XKU_0LX_DkSJ!`U@Bj7*U`)D(Ws8aw3_GXj@w_ho2BGGL zwiATfxe&{`&#P6Qxd=X=MZwl*D6ys@QYh+f%)6>`O-RuIz5HjIR|HsLMZ%SKc~x*> z>gMsvS#~UGiWP5E6g(w0g!fWaR|9FflC_bpR7HE~^V(egC1S?1RocFS!}O;}g}!9` zY^z_E3?J;yv}$S^>P~pXpf%sJ%ShA7h{5idOo(Mnm~;XdDHgX0lzn1sZ(|P8SJC3{F;Vv26?k*iLqjC!ITdf-J7HduWHfwn zUgM~c_m0*j-bSovV-y)=-p|N}UKlSt+6o?jo~iIecZ?qR29ygJntn&`u^r?~IXMN} zRPNs;Vq(BFY)n%AJ?loFqi1{@bF88~>Wh3Zto<~j4Lu~6e+GD|E6>~3&)XtT)WmqJ zKh|)JO7+@wrUEue04;GR0E$%4COW#92n$bbxOt3RjoF48VhU(gU^s{F#QWU46YrCy z6o!Ejr~FEH-@)={?YySMKWAH>wzr>2{#lu3OvY;(Gm_v$%okmm=c4*^ta4YePJjHz zF^dgVKZlF8yXxJ;$LrqEfKu{hh?ylrJaSBqP^g87z_x6|jeHRcm$#cf<}CW*m#&}a zW>nuyrSPA>Ag)(#+Azy~>_k@|dO6#4SMNrhI#vI;mrgg6U}~wn3ws8B1QsVNt;CMo zz=|#@3!9A0fCky|gwXx8;~#6dmw!gaqmR5?6!H8mNF*`Axg4@G7xzgArlH(9npE3$*Nu z7b@K9TbzgCtrE$UvlJNSsMetsgBP*ps^@;hQdNA&dHpnTXs1zc@ya<{KGI^r+02M; zI{0I~@&(rh<_1n8ASToOIJElmGrG!#$!u8X%&1%w2#9`K&kN;(U!&d0KT!DSHPW2K54mwSc3F!|7NB`hl32^EL63xhfkfSCC8MfF;wC z3k`pT$IU0@>cnV>yW70F#_7&N9MrpA4eCT%$Ua(3Raz{Z-*_O}ehenh z_PMq7;PF#Zy@1t)KE@MVx>FnUaLy%@dAd_X{LgJ`*a!XB(%>mN&0i0(&!KxTFG%Lh zX?{Ewt%Ml)s%j$3HP~%13_cDz?}eDqaPNf|31AwQ>zZlmX0NGJY{xq5%(CS;lNtPi zV(=_wm3t2rwZ{6P?%1l=ptBP%3C+x`GOo`m88hqG)!3@G(rarn+0%OjVC;hb>3D}% zZzo7P6`DCr5(9w_`PM4AcG-+|`bx=+oC}|MAd(rLX1xiS&FU+agtznf?$l>N{QKrY zqY8>4c*%QOtJq-7_0mEhmUTing0+wYW?fi5TGe0~v~;PD7=6IiJ|6Y^+mYidwdTNwl`64n zfS0Fji|9+KbGC`ngwdlz5z~Pa5fJ#?O~LLPC;*P_MG8W7NY*+F;n4h8XWzlBxx%>{ zp0Ba$B@=71H#ZnK=~Lzs2zYskQMyDG+7bKR8swR0UMi#pqA&#mC<2B_f^;OeM>2*1xRgK%egB727%69|j zC4DPZzM5Bt+3RP#XTO%~+*=c>7XzVv5n&y}i(x)RP&vIDksLqedF0U8nI`?`R8)Jg zsOjW=02?#BBk_kw3E75@V*ZB^(Lob-%d7jM5|!Ug%E8E(lvd(rz4`*5ob}VTZbY+) zRM-286b8{72%p@Fwqf*UGo05$kXL=bDqDr-#GZ{vj)jI~t+|R1N0(I-m z#hED|??006^orLAOF-#Rw6ENA*SP~-oid@iiNY0>5UPntAAA1Y+f|=<10GKd5#D5Y zxxwrdD-5$c!dPBkai6!Ej=;T&sJ<3SS2Ci9FAhz7QuUCT8%64HHn^>gHshp9!F{Z) zMDtyPInpo|l!@>l?Lpo2_(#uY}Ws zh}=e7=R{exmGoLl{++&}tW53K6!@&~hLzKC1nECnI6mxWTlf?q?yhDGW@0hTvTHP# znl~gSvx-^$W#U_z1>RC+L>j^P^S>>>7YRgWlJo9@T-?IX?74;r5cNL(^&$Q0@cY&0 z7_Z;N^;Wi*>YN$M-r}*0c(>1L4InBbj}u`UA6E{bSILc-rC~%I!%)Z#xVlDu37+ko z>27`CifkserT@1Y;jFth-08eGncs204y}17S7$}c5UAmEG4YTyW~kq*uaLt`eSE#O z-dRE3=H`U$03RBL?pbJZ9#AAspV8E+eqUn!9$8Sv9S8f_M!Ph~fGOwtv@yZ+voGa( z%g?u}i_vd13_yxW=pcLTW(Re?8WjoAai-{0*B%G{ZoI1vA1kvczOpuV$k_~Xu`)?R zFO`LhbMv0SNdbS6al@D%kx*4!OpahYj4y}hELayfS3i~i0PU+c3$tQz#tH0;2MeWe zivaX0dQJ@D`}fwa>)zSjZ|nL0r23QI+FvZ%3(#TN;*y#yOdSqd(uw|d{um{FHmvEc zjdyp%U*@V@X(LwZT%~g#-Iq@E$>vFK>b=i;70uE%XP7b7FuIWTNIUu}to{U}=ULck zGO%=Cfj=_={_$-g0qhQdWYi%d`ceRcSe2yZCu;!e6Jpg}n~u2Z1QEOA@7f3O_eBmc zD!lHO^R0jSKALF`Ck)X?oGhD*jAO}xRjJZz7+o=hFxt;Ff8G#avg3qBnWU$xg9;aV z^42prGrRm1*mTb!fyuGTCLk51!;8c0bg$GmaIZSr*|XB`UME()!$)Cgh&ka5FPtNV$FzxY)ukSwC`w%=~W`Nj&j&6=gr)XqPe4anQ7Rxq@GSL3)E>cXKpabHjO5T|ptzdK`S=v1tn++b~)!8yxv zTD`lJQ<)e$PKy8{P3}^{p+1p_|2J6Ua{iu zi2F!l9=05re%!8)lySZYx>>)WP|@7-%KSdFy!XRcTS|l|^);%H0pe@nE}VHNqxc?Z zhaVb7pe~(AetDTtG9Xlw>&G8;Y7>qn53Pa{l>jWP5$VBjJ%{7-Rnl~N- z?SrPCjo+M9zRuYl%-)@A{8G}?^f*{qwQJjPALG`{Sjh}V4CH}FhGE@=d5bgu3y=y;q?|?VQ9lYh$d$gNxzNMA(7>HGBWa~Lx`*O7 zHE7jP=#&=`{P2n-nXPiT9yO~&;b6RAu5^C*tsUb$t?gek>ke13W|U-uw_W)9a4<+Q zx_>ra%iXV6G_vmAQwRRpq;v}0mE(_YG58 z(6;G-F3!86Jm`+3u(Ih>uIS z2(m4ooI8oR`1)8QC*B1wnB=p4xC*s5*{U-+mQTaUE)M@7D%bjwM)^{(SMrT3cj4o? zLL1|%_yAmch2ksA(%ut^ty~j#zWSD)HfW`N8a_ zTFo^V{i+jCuK2uo(deGqVG6q)H#@H8lPz8*mozG5J(748-^={mx;!9~x#g#p+x0N~ zD&tWsge!!I@$u7?B7yfG7i|7L>d9AN*5bw#Ga^TliTGggTtAC}hE zRLXcj)=8U+xB1QdJa+%6Rm^kru3T=*<+-|xMURJF|LZcl+ev%!6o-Gc`$NP@^SLYQ>_Jaw6S;29`_-wM zr{~+EJg2miSEl1DEY9)7XlXBiwg+pd$%V_76b6S*;3b74xYOd%mFg098Ae6>6c_vr zMc(J9$q9y~r%a)}omPVpG64zW=H{uJ%;PWg>=AVSknQ5#j#d?sb;0To;ZF@#0x@e& zwFfPkQE${HR)8}qX~5M_Awo%}?c|eoK;2!kr-`#Aq%U68afUr)EKQX$3I1IpC}h%a zDaW%A(LYUiYKD?yT$wu{X{=%1YMg>oEf&bUxJ+4{%^#h_QDETlov67<+|dcTx{Ngb zdNlrlTQQM{UqUIFVc^hJ)3q0mD3*YBk7%PGNzBON3)NI_h#WR0OE!1BG(8FY%~1b( zayBVvOVG_Z=N+HuR`gKiObZMKGh776#dOXatTyM#udxMCuq0Xe0X~ejwB)yokBB71 z5SHYkj)`NSf4El?%MP@N2s$oJ=!EQEFlnSs=I2f5=$dTwKIaN;n#Lvjl_br(F?Js< z+DuykzI*&#_MA?8sjzQfznDTtm1=svX^q7s`1(7kWYN8x%vH37Mo|gwE%|G^WY$rx zu4Q}KeNL=E#wFh`2m{zC&aUpn-1;Z7G?0;DBw|tad>!u`&{4vSqQaJ66O&Z$6w3GT zO+8~3xj$t@nB&b9`Q#p+gAZGti1blHQgO{3KNNM0a;{W?6H`l$AJ@jf;5{q&uPC;l zgn_#~6)R;ZT}DC-=?8?ZN;PckIl9T2)F*t=tA8qilM>+zBWa=~1;p~CgB`cCByYsb ziMXA2nJ<|=@AyWt&vQ8gGSKYEg3%|&Al%>bC6+MDd?5pvNs;L*;DzFF&Ma@hnBPGV zk+->@nRCu9sHTOs>oR>Yx#^lEeZeR4$$45TROaGxJm(!vh^$^+v#SM}tOEtTqfg5u z&1W2hJK;I8oU@O;-hco7%OQu3J3Y zq|*pfZ5k+HpK%k#*96RIGgy5#*F(arNRML2MN3qe&VndNBpHAX__7vzRq}2W)}>?h zA7eWjd)-Myy6#gyV#P3XWt9O1 z2yZ$8AtOW2tG^2CS>l0dLRilY6!a>B8L@NqFjk`EJR98pv~MK%l-TV|A~Q2%qB5C? zU_ZTEHV?cN83+wr;bwcC(f?`!$G{XBpS{xsY0de3Ai7{};G7h?jZLQH`x!5U2@(rBD?;NTM?Zj!X#Ic;7(2|EfHtdsEFoaavkbk ziVa#UZin8djYXjkDe68Aj#YA(pT*%eS-`HLlPY-JV7V{fK3OgtP=K z{WlQ?ib(ToZl(91K*O1OfjOS=eyr=)Ywj>Sa?iu8V?PoYnRI@kr*}Mdm*02EQs3?Q zA$}6z_+51lMe&})nuHm43~uX%$3Y0=BuepNC$$kSUA7?t22%R`We`A<;8%$_T^7+(~!JuqRPnW%SFg zMQ61&P+UgfwFXM($YG-8?hfUWBEFct9{QR;0CMD#Zji0=|Boqpj?I3sN2?W6iz~t@MF13a1+W^A6+^P)`XS{MGE7xbZaEW-f*v{?zud_^ab!o=sn=Wzp-Grs7`Zz>1AH}5y zaw}k}?~me1={}0BdFQbq3=WB?{2>dA*`~D@)9^vh;ih56UBr@-)u%#J7vVOLkVqUx z+WN_jtpZ(LFNj-qmfh-};dace@&l$AK4GAiF}g#CieI&>j_;{?^~p-D)+ENf=v}sO zjQylEGP3#@A&Ux82x=s-!Xd&akZ&68BmOXi{xUyOvk+TN z#geRmgM({uo)P~CJ?d};l)L`MNG+{#q*O+{x9vJH5;q#+5%)&x; z$j@BtLuPu6A*}IccL4TWt}J}6N$xiq8pY)B&5eB7q~7xW@Q!HZqAxTFGL4f@Mb^MW zNsW_ozDr?!oX;cgscBYsvYO|O9Zn9|?+O~mvma(2P5owdLU-;jf8^tS5((pCt3P<< z8Ui0Jui$&vlB;yyv*iPN8MVeKVyl%K7_|%MzVOYp2e}GHrA)0QArR~_-!CYfgeA`6 zGlb^7M7D8EpZq(!$^EMSRxqVr=@2F1X0Nq>rz-m9zP-!+Z>?#Z`x?A_g8z{S%A?o^1B={v9HpiFOu;ms{f*I&ivSv{lZp(pqt&PZ4)_U;^lm`z)|$M`k)AoV&%<862Li6HOG3_o~cl@Bo#Q8bApzT`j8m~yUq9n%+R&fEN0>;_^zlc!VY2kvKZSRuiS@0PGXWYouK=NMo+Jz zIm!F<-J5IXvMVd5S)-ppBW$qmiJb4m>r9FQ%ujmBU} zIpWDY;vxikWS@UN$pLl#XUJ5oj@hP~Rf1S>D&jkC6S^$jQr3sndGBOQ<)>_?;iY1dzG3`m!yp5V z7c3!zUIniA1BKL=#*M#B#bsY2FWrkWsin_DV!d{6DS5i=U8nhgi_U0`xDvTI+aPqx zLTrn4^)_)3-Z~zF2AWiS#+=PekDd5#;647TDf7~pore|mvuF9(*ww|FXF)}T7>Rr5 zM!O(pcGxrDJ+|uyQIzK0ojXCo;~HG0x95Ks?KfvGizlNg+{h&wDaxmvsJ<*%CCEk| zC2SdI(jp>8Bu-m1b>r>*SU|zKt^%gKgD5xvzQ*yuxeY2TD2~E$K;x8X-smzq?Y1RE zJN8o<#Qyhr(2Z|cSaVp->+>{fjh-TPDvNOiZyvBJcVO=u>NVK~r*4Woa!*KO5?FHO z5wq!15@JM+1J29$z(?%C%d_mu3r?77uOVdZ%>zTm?JIW@ZL?^z8o@!$^<~$!089;m zk^8HIWnp&aP4+fs-s#mZ?{H)B^3q}PY`opbbmNxTIWTh=)pbZhV$(Im`n){IP~$5$ z?P}XIPj--;j_;mJsncV=t9(va)J|4QFzO(EJ-=ug_OMm5^FhjsLh~DUH9-BSO$!ib z=YRF18e78?-{xT<-&Ih63Q6V-%nfk;p#d7Kg0Nu)LiH+G6lHLC2>bg-^GA6K;@mfzL}8}5XMZWcSpdF^8V+pqN#Q@jMctZ_UDoXH z!d?40sq)=fMl&`0PZTT+t_l>|JpKB&HRlTwY+o6#&LkylclhGo^6qB&UB@iOzl}yFp<)=1C7l$} zk~Oye$MGd{G(*VuqYG!Yc_sI6>hJSGp@Lo*t;A|GVW(IK`9kF~<~mdr9_1R5CWgGU z-_3OpAEuh(A9veoORbUem=ol0DI} z(Y3Oq0EbAPI#;T;amY_*3>s*Z?>2%ci^p@0iAiB@nAk&07l!!~v%>24;zlV+K|}k% zYN~b{DQ00KB>7^=qzu>P@-L3SlsWtZ0)FiC0AY)Zp?Zc3EBR4+skIMVL09OKBc$#&@-i7-wB!elP}PNQ)}*qG zGP$2JMAmkQ&fSR+G-~r3nd4oiSgM^9`=#MshWmf^(ls&@STT{I$;-=+zN@$0keE}5 zV|)866(yURGn<)2pNdz?s^A7;!87#rc=YFo5G({3ziju|?>S7?^tD=Wu*+3%S0aBOjMwV9Kq1_A!~$_t7~uQ&?$NkJPkGoVp52?bLC+X z*`?XDoaL!?!N4mD82}CbCl$@T+Nn=*z@@VGu;&#Rh>qxlXlmwpST|AzWrIB9Z@&li z|MdscVvQs7aO0q0J@fxG-|b*@vj%ti`l$>DXNmM_sz1GeWC!%rI7*vmiz=5VnVKQC z-%+mLuFY;DdM`>UpF*ox9u-ZBGbr=%E%+Wx*EqD&<5F@fO^t`0ZYfbH00xerz=HA1 z?ChgIprNeh#r6a$&PTz;#YKP(G)SSZmfSB!s$DLOIJ1)I)YdN(!0$AIc>?ldqAbWz zKBR1aodNqJ0W|q**!k;8ncl0Y|HN3BH2^7WUWzq&I)&1Tdx7Z5eT4J1L8%U>K+wVFCi7s$OGUQ_AL2(lz zwlRT+Qc^Zxa`MT_aavI_;`RY@y|=N|V3&EE+lJ=VHv<;B|6LCYHJAxOGZFzb zmkbIU1?Fu7SA={!Y4!#{UP(^Q5@5K2g#fJw_)~VEbys5xHp~U!;{NiG2}JeTC&Swm z!bS*meuG3+jWoFay*vj*5}B$SAR&_iZ)b-{ON&1mVn%HL7t8k|lxm>_tiPH23LCnP zmzxa%pJqk?-7lM}GO{v*j9X@yXMSpG1Jy2!KEe#Vv0P~LBZbN8i9ewD(bIXAq(|Db zn`Mp2QYRw&h%FNY%n!Jp4#<-k_4NNSdcdjS-m3!=IBVvq5-=cO-)U5>MaW@0$2j) zEL!a_$>yr6s)a&*rjO*bxpr!?!k)vRb)e>*A>=AJ;3{Sx;wa=}4Tln?fm*umbACB9 zkmrJ>kz(EFE*&ZyV6o(6EBb4eCmpC!E=d$D4jOY_6OEBjS|*@`)gpmFilfJ?ymZz3rH{+kB*LJ1QMEH2D;)qe?NZ=RPO;C zlugi}DK5{Ck3;sF6AMAwA7tIg>#k%ndr=2nvfgMYU}_*5`{6qyB8;e#Zb>S50cYVW zi)^a^bw7S>g`|fY#kgi4Ec)Zo*h!n3esWr8&}y5zumq}eoW?OI8hS=zv-X}F0CXUMfSrAo=v8L` zd>OG30?v^w7DC-p-2UxGR1%p!=$dEue76H>16=pH2NF_|S%ua_C(iaf>9J*tzokDr z6%O;;eA*l91w(;A<<$!OY9wh!7R@2pq@ zl*?R@?fSRDHka>iGp?YObD9pT`7&RI1vsD4Lt03)cZ25$5wjKRMZgqA_gOnT(0*BP zNaR$;lpbSbBEtm{R8DLZ+sBMfK+K%@#e@lKJya-ktgbFN9N;BS$j{xMU!z#3U4L*6 zhy}XHRN&DL>M~))!jZBBrubV9o}FE%)D9~gn7`Zj3&F`cSW*^nzf`J%gra3#IiZkI zUj(DhgcbUREKp33^$lVj0!gTJRKM!%`HSt-TMwcctBRZmCPr+&aX%RZ4NAOi_HZjH5nE!)LtWeX+ z*4EY$96g+UTH(1o)R`Vosczl0zqI~va#DFv1{oS-poYDBco+{RfPP>MS@Pcn6zm{D zgh#{-*`;a$RwR(vmEcKF+}<_{i^Mi-BHjin614dyhY~VwSQ8-Wj~oYYRdfbeUshOIu>xPkvV^@+ zCRC1qSUbvP@Xa3wWf$n0gGrf58OidUOTXm| zq=1q6FVXR&)R#f4BVL4=fU8xeX_lf*=n!dFQ8_yw3kbB5K^Dps!i8ofogiQ(-iEu` z>Bq`}^!6hj_;0ZP>DIQv!T9Oc63vZ5@`Gs_vZ^pc{ia)V?=3a?b6Tg!kSx7lRa6dO zputaelOpL#=D2RNA_Ak~pTv-I0mK7B9S!}#;i23Q57QoQD~KfF?;N zr+SN(7PaeDFE3LIi_+^oECg|J+E2VkwPu-tkWwVnUwR0nS{_kirlRI}>iX|REBjV1 z$k>7zIS)W`?EArKh-D3=hn!g^rus-1j^75;~K-jKT?1kiQBp!zf2x$!z zsWbCR$kY1&7mxX7<*AqFlN4QG6r=+npx()0?AO7BgB)UNW+wAPOd>=swmtWMuaGVr z#D>Xnb5j!?i&2p&nP$%5W32`U7;j}r?3X4n56B;yy{<7DiQO7XqSQ*!mttU(>2Qrz zK3$G|d;(GJ(RB}bXMp!mBPEm|jMhQMiOMz&Yf`#6IY}bj18N*fi2TnG*t-5N%6v20 zd|Jvne(;cgueXfLDF2YmYi#xZu$qUL*YN57DpEPt7y^J0z@u7NTr_lZOC8SS)V_a! z4w>4|y1zIZ?m${YkqH8MI$fFpl_nfiJOVh?^a7VVx{ zks*_3b93`@jPgH|ETW*1um78r$x4+HLE@mt($TYmY$1abBNP+k<2ql5z}QG{f(S@*D{+{ToF_buIAcayrY+A8zp%MUZX)BYnDu74Q{i>&nXHK`!Z{Zz8b6 z52DsY{>1`QdEkClS*yHbZT)vqIngKY*c=JHUtu7O2Ow^=G0dVPDnfEBA&@R-eCPe7 zlM@q)kfIMEF!sNvKLac20U$>F1_^MiWHz$bfUH~i2t3DP$zoAV<{J<4kuh*M~j^Qi`2h^MgW=#u_4f0TU$$}u5JWkLpt!k z@J{&)s@{pt%@|0mH2+tUkTu?j(t8JE@pD0<+K`MNr|XfeFbXov{{alv_&53zU@i+W ziU8$D3d}~*71@ATSzX=CcJY59P+(OgEte^D%y#);H+ z+6iw6%8>tsbSZH`cEJ{EfprBz!*jIsz0J@1IfatlqoV|{T*2*v+!{H+F;Pv_WVwRM z4l62ph>d$Aa7fB4DJfYf)MNS>k+|P}N4u8!lf;7)vGz<)PRr0_>rdZ_AABG)B0N|-k)b_PU_W}*=Kd1dzP)>~)_WtB$v%0*_+vQYk~8QbeXaKlG;`ky_pm!AV$UUJ>4`2~ zo88G?$vjvUMZtb=_wN>>tsn+QuDJ}OigW`sm(A$+HxemM0T~r9*msdWdSlJw_OzF7 zRU8`@>eU7zc&@wI5^{(kBDNj|O*{s`(2jc*(kFe0@c9%L(&EYhOpA7x6Ozr+@t-d` zmA(nmIFRRaWqc?9C7!Tu9e>ZqoU-bEA`(Zp@K_mj4Lu-$(>^^-7RKFP4QFr zlWVUf-3P5zVJ{?B^9!d`3c+55WA^EhJA4~dlI?uYfr4Dix4PoWKn zO4Gde_co`vHf{r*2FXYGf1jP*=*&~lj*;0`ns9BMKVhl9Oj|@QOU@h+iQ_^8-PNvY zky}e1E6!pzKkjqLz5@cI*1^hy;DbO06fnWZ%r61P5rFJb-;1>r*fVpP{k;O{cxcCp z0#4vR%`5Nms_O|3xP%+7`9aa`q|xm*8uwo4MaA1A6Nvo01iHaHYfs>)h%6;j4TT~h{C>z<0|y{ z9ShvWb51Ifd%$YPT{c5R{s13u6YvA9X8;)M3+J1*GP3C72- z8Fuq?<+h+5h|XluxwSrX18#@*k4OtNN~p(lLYR@vyfz}mzv;qpl=+o7s=-%a4_WOs zlV0Cm&v*R?cHBfNo9LYIDPUS|3h1Hr>{HAT;s&2qwP=Vo)Ns7jM-_Z9*geuR(F zbzBa7)hvlQl$1NijO`0JsLi~QKlDR^_SEn}$b}4>Sah!9z?m7q#4G~3ZbhlUNFN3` z4MO|@bN%L@kCShtwaR$kf0W!H_!^MS)mxGzAdX=|yv3<2RQIQ!Qw{C|kliDm+=HXk zy=TAtC8z!S)e5mh^2s4;#eTrDQqnR|n3{XS8+fLE@%jlccUnz72Pm8Tj;swgU9L`d zzsYMwuy9ppRVr1DDic9e_CN0lTprxtxpT?bG?6SDC=XkLiNFI?NE$hz4es1WtHs0I z!Qz0(VU1B^$D$*krS|ow2@Q{+h?EQRxVGaFKHRel5-^c$kUH!^;b7eAf%?;Re>V{) z3@|~nWpG(~$sNo+lv_|LgL7ocauG)jdoszJ02gaYT;_c-fm|#VzsW{*{1mXY3LWTi#W33eIv9f$>gjeL zvBIA##Uv`1xAR%q$cD?-RoNz6If*Lm)PTK-Tr~|s{|HZQsp&pg;aas;cn$ma20r` z@sU{y^<&ubcbVcD!FOdMjzry;Wetf^b>2%HiGV54*_GiJKqFrRC_CNt(yU8Bk8y!0 zKJ|(+; zG$;7>kImn7HjFn;W6aFFqjFSFI3tBO(fU{Ww%mayqo^!4Fi|IOy6yjilzx43;N%vY`^n0-ogiYXF%^B; zaDUZsd~-5scorl@O}iCxIco7{f?%tQ#v~dR(ZU`_DVFnm%%8PLOu2v5?XeU-Zg#De z;Ns42O8-DZX1X6(i?fXAJXcnCH|oVEzQ1_SQ>|s6xnS=4`bRHvCjftxxAd{kmE+|y zw!<{(ijY`bF@$Oy|IH{rc}$TMxqtX#gR^_oVb9$Hn~-iw?O!UklY-*fPgtxx(NFE402!n8ti z|DvMQER2$t7pTzjEj<3gfy{K@F^xaTdFXUHpb{6`-V_0e^=n4%O-M2=zAeDn|q&3}p zHy~N~qWe34*wQCy{*;caG%cBrWFnbaj>(!;#r-%kL^Hj|62akUU4)3&oE27+->V(C zqe@6M;W@>e%Xt8YSn384Zx{g(?s;gOkI{Z)IYxV4LhTcfZF&fxci03>G!do%FV}03 z#@lGvEdS4PJ7<+K z^Lt;tZm~%^3n9nPQMKb4H-Eox(pvvsfSHtKi|6{o)0%EDG*~=*Zol%h9qr;c9*jWk z(e5lM<)%}3L@F9=&tzm&_XBx2QaW<8(uw!8Qv?}OX~I@>gLhqzz)ym*Byau9PU+eu~VoOb9kt{Fj#4H2-CR_;%$1FwVH_Kt zpT?TDl|0+`lm8-+k=_o%eM5{#xU);VIkEk>~JS_f~hOg>3+WbQ3UHW|6;;>T#9VWLJKJWv35K zR;%giTz>&&W4VNCH0L`Cu&ydV zixs)C>16ggT@akx4)pWx}L&Q&yAD{SAL$b=}v#1~?FQQ0Yc+-H}o#Gwls zlv0Lh$@$2=?tftv+5pBkSOG0eCKjy1TQzUgAi83vksyD;1ZlNPE!+`jjAwW3n?#jJ zw=td|2WTL)3?=Jk!!nd#Dx0w5w%d|v2JvmM9sdF*2eU}SgN6w<+78yC5?nIe`#J89 zMTYMt+g@TxPn><<(9f)!LNJW`(*5<}8CqeKfo>q}Rrk#@J6^!ps|gL+nMwTJf|)Ps zVWZ&}`mHRCo4L1mgf@w$G%n(JgypwP{u`w8CRm%%JvvVP(rR{6B)ySSmQy|dhUY7N z+j892#JF#OC&{kF-_}R0Cw1<@qpHqEe~zDtji4rlpE}N|-_6FzpR(Bhx*Ck6rH0`} z2iB+YCDJM!BcB&;-sgF~&rCi&OtM+=m>NX#rUTop`*(Zdnfj_pTgVMtF$neT7TvZc+-I zl8CWf(JulMJJYREyexxiB+FkA*F)GfY@grx#ofKOpo_=ejK`z7^jE7PZfzhjsXnrj z1-v7JbrJN5rKo)AzTx522_-vl_USjHhZlzLlBe5^=SrKqJc=f+n25`9?85%?PGCLR zKOzkyN8$up-g&pWUCJ{(ebg`+6AvT05WW8x6W}g?@OA#Qqiy2HJ^g*~bRhX{;q--g z`PIhoUxLlW!iy2`koB7Q5ck;)keImnwI;9DR9$eRK=F=xjM&SqDBw3w1yRo>l$f?e z0!P`5{W=9(q7G13OzsL>-BVyGhWGBBwf3ZY-vc)ri_W7Y_x`jgB=$dr`xAu;p(&kH zou;R6S1ZeULN}JJGb}3=t%XlBUH<7k%?$rHLt?>N0>`dA?dPJ@Ra#94p~+J^H66>8 z3BREvj#m@I^xjUcwjLRVHvPUhS&3WVCnh%@B7t64IB+N|3d<0{kVe*0}ZDND?$=zljS3DEr8l?2voc-B$HcJW@` z-5A#v?@xMI@?JyI-8P78k>NKYIxw{ULKWC-@MHv<=WzRW_{WN+I9hM1=TCj*I^M@p zx}1v&et|CfrMJTNgbgq>v*BT(hf3%f-RJfsd?^!$QB17oLS4=u!XlJ3(qA z?n;$6J&&nd9bN(z_Z8sQF#od#CA)FwY%&A+ylVZ26*r8cO1NUMWF)L4t)>$6e5K~# zLLszlTRu7=60~hqM-@xrahoH0>cZNTZwl23# z5r;EV1Nlw0(C7pr$BERtI~`K(`@k)c)|kLr3MsWt!Hc_G=X%eVZQOQxj*2C~UiUYz zg!Mb&!f%ahbUOhP)1lWf?xrd5RN^zp^vb#^K$Qvg(h?7lqvwewBfCeaCFrUDfpL7L z`;7pywS|6W8~01}=>7daUF(>CzASet%KIF@HT{gu^?Yd!kl!K5;;PeSA_~H>@a-R| zhJ((M{tMs|c{`Bf)eg3eysvT_#L=G+>Gn(*lm&>y5Bvv+JKWS0z|x;F9s!F&XBdxMy8}?7PSMk!C(j(z#Y_K}zEl2Q^3XB{6=Pt$l&doIFrV z!UAVfRxUmIhm#6RzNz*p7fSt2$g67|;=ykLjP(p%aVj1~f)8loW?ZB%v%YLGzQ_?7 zfKUkS@5o^1F#pDk+k`|59(Ttu2B1~Rc8RpAUZ_JGCvdwoYG_aMzfcu*r}o9FQI$>8 z#%3lrqDsUwRpgOmq2?-Qx5}H5o}s~zd}!QFWhxUyFKs*U{PuEJf%hm58h)eh&}@Wx z!4psrbLD&LLr;%}4WC)J4-%%>z9~0o5u%+QAb{E}jaJjK1*-%Qt zsUNHqqU~I%z`ui_C-%0wLK$($VMN4bZpdmZtp4R3$wxmSO5kbt z#-|*9HfPtiT1XB5JNR=(;ZkaM=LvhC(F=RNI8txhEf0GF7OA^y76BEbD^X)E)#r%x zX75gJa$NK5uh|S-_Kb2b&z=8fC-2`aY!6VRE0_8=kkFPrIL;ByO(^-Ptl8*yr5NKm zhl;w3@urV#ufVTdK5K{t31b6zByH)Ew`wF2{6yW4E^E53__8gNeM4GhV}sr{4%q92 zC2Zw^(jvMkKih7+#w!5=CCauVH**N z0Uluy;0k-Gpof|u7-aO)Py3j|M9KwKUk;jYBHq68T_Uni+@uO`bz;8pj>c;0x0p-!S+Qo-n8Mu$1+|s%|Ok zo$iFGv~#R6eJkN@PP1mg6tj)FIg99jD)N!LvFgwbH0i^o0I>+>8=o5 zUOPh1vCEdCl}}ijsT`MF%55bVJvH^HpaWx=CNQ-}$Cs3b>6F;g#!9rzi>hVpWk{Ns zLl@yl${hgB@+jijocatzYDI`%DOC`~k|hx{62z{RC8y`-tH)p*EFG(oCr& z99qI&2UW?WWRX}~d5J?A7d7_R`15JVy=H-vmR_mu%-xxIRDpC?gMz2JSy}tew zocY1jN>BBtF{}gkV19`%q@jvsj4Tg|6ee7(1RZQ&lxW=K6aO~?L{QCUX_@;tKG)v< zmqv!t720Y$SFspIS;;}eo-xtRVJJ6Ez4H9OjNVwL2{t1k8YDus!RIIWPDtY^PWSt_ z$P`~XLCGj$BN8DZ;i+cCl}EYnH+^Xe=BQLkIU`eJ7iNB!C6j0PYhf<^4f&CtYfPOg zF0H(3FnE2}UBKmzn!<01dlR&+&<3&io3=@c2IiFLO1uF~Fk*AeLf4qm#sXp6OdUf; z*X^g;R~LnKmgFMNtm&_NRfx%ZU(_~^BXb(Gh<|YHfAhR^b^i*Jzhl|ygd-!Yi22Yl-{mXaJs?N* z*@rZS!6>C!Mh5&idx2FZi1!i6sAiLHpIf~G-n z(y*y8&em@JuH4nV#=}@9tX4gW%_dn74=Xd9@bBNTv{{7=(&Dfu@FZ{%$eNQ%7)Yqy z5jyI1e0e2%yh%nvN5vxH(w;`&KDe^_`NWunc6{{L$%28@?7Qj70g}(agS)_maNHw5 zkw$s9SeMNEYpMqtd)(bq$#TKbr_M_$NteSATscNP@g!}+&u&aq0X<+-FC@7DFPKj9 z6rK_!ta9-ZBK#{Ipn8R?A{_|yqiE2{a;&ZlVSoM*m3=hKXD_cwxxl{mb9+4$t4W`S z(+&$!k?h@cVZRU&CzWj!Hk#}cwe@J})3oaCNuu767RVh4qX2UOy#PTWr=#Fu9 zR+!5ySFlHKo7fc{RLm!EQ`z8h(Oy!}%i8ZZh8{AWe+)YJVfdmge_8fJ(Ab9g$>)Q9 zey4FCR;Q#ydag&j+JeJ2W`T$t$&5^*dYM+uqW{nkEy`Vcs7&dk}?iz z@+VlYG*th2r%3Ee6U;Viq@C!iQd~COa?VtS<(M})BZ{9P;blvbeVtPy-e6laJ57pT z*RXQ;qxy~fmy_H!#)NOw+n_E&^1@~BH4C2tNlhdKcOomxlic>Tn#uA~VVdE8v9ewA z9C^Nv>m{)}jmy~4y7?fEQ`r_W_3rx!-)goayf%%Be>p&iTF34MX!GYsWr#zU&X(3F zC+O?<@=sl-NLq{i(v7Ig3Iz3x61!F$=mb23jl1{Mx%NDEhHL<4etdhK+dZ)Y6#;r2 z#Suo<^oE%E3Xgdlc5pSiV_&6QI*@QkZ`;3S*%wVk}=JeU4nD3=hYW27i zTC=obSx~aS*%v8vvyHvqPk?Bjj7Y39)#hUnQy*^5Cu5KIg-_ldjDpuXf8W{({x2Mq zNCut~!|G@2XMHrP9d8(+l}LC1P`T?&-z?frJkNCYJmDk1Y&g1ZFM5pSPrEFTn{*5* z6=#fb2F3bPmc}CNu?!kM!2}k-NBxZ+A0aikdgPB|s`22JW)23C*TbCAhRMR7H%CJ< z5oF5mXNDWv0&0X_tt|h`YQNl~YjV4Nwb=4S|H?jJz@3Pmx51SL0Fa8TmBAA)J4za# z#pPTN74eMXwAk`$#L3(L%MF|ZY6z0t(#X}}3l&Bv zJR341jgqr9V0@2!ow=(TxI*Do;N!NpVh5@<`!ZKR?A-HZ`Apy-r<4*)_urYZiOPv$)cNSZYt^HJk4T>v=J5?nZV zD$$QksQ*)s9rVxWvsD91i!rJ}fHA9|fJzD@BF%p!6gq z9Qb`l>@PVilNQ+f_=bXq=(LHzHc`SF{U0dIkEV-TApEaoXgBY~3B3+Ri2M;>iFUJ& z(%hUf2Mr`X>j?-o2VQUzXgg5lh>Ejub@F9=C1UWPO#6I|pBMNRQUMj|k5U6>%t1C< z(~&`1CiCse{NXx(^4Dc&u?UQn$Uy!*MnfbOB@Ecn+qA1aLWUZ2d)Qsd&57!S(88_F zf6n1s%R3iyvEmRJ_P-~R9&47roJtMvsGO}@5HCvnxjNfZeA0Koa-Wz5VSZAr(Dv-W zXq$MozqgS+lU*+vcP%QA`xRST9y$(NF$y=Rgnk3W&rMSyk1pUn3sLIxS-t)+FDg;_ zcG%ajNk8F*<`(^wlZ6y!94~3ydLd`y2hw%Mp(iJYfF{r5obH4=ruqDx=qyemI)g;> z4cy2jz~M;4e10pa#o^J%Cyk!^!JAl2|K5H*q<${j9L8ehLIooOu>|> zTaQBJQo_k2RBic#EcmTPpixh?h(V0EjK5b;|JT2 zO-?q<3Y`l4H4^3JRTzCD9AT-=dd6(5KTHL$)xEdewP{iz`hCwt$oZd*`{=FbU-n~o zJ{zn+M6|uY#$4;|xzVFBm`zupjWFHjEQ@P-hc)yV=K_fK{`?+cwNDK{ynnB)UV>x> zEjUDICvong2q6e@!n3@c%u9dyqTpGHu7|FLP&XHS(2Pk?HT`Tmf1) zdo}C7aTWfB1p!1xpE4GKUte@+uOBSV*M(Ao4*>E{ljLnj*Dt;W2t0`_!ULb=pjpUd z29?`*pS~iOUdfqU(w}8B#r>0RlMJz&VifA9hQdc4QH73Ni>$Wr;w324x4TCvrZY5r z*_XbMJ2Xle{L!y8jFTdey+k9nt3J*gocSGFY(%9f|6yel(X#pN(Ts}Ta_O-cziGGJ zETM5txnrEZtcNG2B zvs#H){f4RBS|gaMY)^ZEjf`gX_Uh<)Vm5h?Q5a;^%xaoOk!nP5?J=y|3YFuTK z-b!2>46i<^9_FnnS&Dsvb>(@TIc*~I2OYS;gFeSPrxb(q3$R-L>8q$WaTj$VuR%)i zv!d;;Hl{YAHVmL&Ha#_O_Y*2HOR$kQT;i;PxhcBUfIE-Ow%D9c)@yw|kU?b}P4 z%hk#l?q)T6u2uPN;i-{9ofRu0L+MRv0=tQ~cN-X@5`;II{blb1G)MjL7Qkkn+rJzQ z@{jsG^bKotFmZY?4B6l2l*v>^;c^=CQM&7LRcEu9@aS#8ueML>Aff1-Pb7Z(&X9DA zf<8ft%lo@2X2}N4;r>?2=_gegS!vn=j_DT@%k1v1>}ySnH1DOPTi@i)hX=*`yeK8_ z6#HnfS7`AhdD7lo&pb1qNT07>0^H>S)#K4JP_TebrJUp8|7Bv3P`iORkwuH0X0 zNpjBmE*aWrB*T+Xcl%-u@BBDHuyaAxYKP!uO?*O7>D-v-MidDx1tr(Kx@=D|rB@Gt{$$%)Jl_(gx}n)$TO9%&2vwer7^=(Y z!{Lc>59u!18#OM8ePcTBA(QtM{&*32S1(by4$vqbzt7;C zhh0IzhMEtCM`6jKwZAmAjasyZS_XF?%hkgcskmFlI?9{IUJ~d+6+$GmVN_5R@ zOzNCC227-|mZR|z5a|1~LMQT{PYK=ERO(FACa6P(>JXwTE+S3qjtEESnImLu92~lM?p)dE$HbDMnW*yv<%T$I7ZQ9amEc8k=2>JZovepd1TTg_&0Db&!{{i(DiheLGL%tCE>(P*H*=d>H)tuAzeR0 zsxcxTGA3@y%7W&<)5bSYnodv5h(@Zl!uDnvBu`JzM+3Euctib{p3E$zX`wI3mq$4W zUN#7&fZJ1nj^)P6p)``3o;8)%)vYpf8uU%g`!-P;W5J@iSpr9N9e;>v`l>aYn}1JY zy)h%u+O(&z|Bl#`jWuOc?t%`KyysWu57nw zp?BHt8`oO~ym@%iQ!8BQoG;P>uoA>GKTi=UI~=Z+_6$8|G88G*!$^b_rtj%HO(sCu zjlhThQYDprL_yS48m@N6ybjhPjOD<@Ea*dNfbi6Yg?Nbg3TAJ(Rn({W5kYX5?6yy5 z!Yk#q&ty#%6i*u*_2sp~=h*ul^jc6iI(ko5RbD8H5v}9vJkw7) zqVHa2tNp2UE89~D*#r?`J$Y}p(eQ$XO_VbUxqRnBv#B>S5L9`hQeMZt_tDN;MbR=f zf%GpYO?IpR5k_Vh=WuGZL@Tk1x>1qQkl0XF#uQ#5nGT~cQJjlD=~K7jfNekqJJ6%I ze+Krnne6u;3SMJ;=9IeO#OCB`l}h1oCqVR+Re0f<6c5YNpY`9VVg|(ZG=aXKGz-Oy zMNYZ79|1vO_S8C(!l(t(rf={IrzratEA!lF|0>@Ay~Bm6S@us$K?$c9#ApjsZ{(@( zU!>63n+8jUdCs8P*N>BnSjyQ{>hM;ZECqmKFKMoxYC{G{r~8rMb1}8|vxj-H)tV_? z#E!Z=kMkZa%l$=<2MW&_(chL}x{y764=X+u%Aht0i;Jb37MF0_$C|-UvuLv@PZgXV z+T4}YJN~Nhe)C&h*tM@d<;io$*0?3V=`o$V{aJYk-0tWWeyk;Am&`0Wvy}mcrP8u4 zfM589uw;gin=AWwcPMVD?vvV!i!SFrb#ly`B9a2lT`g;8D6T^95AOeN zg`{!VUMg`!fKOEFc2y(9O!Hy~%{)cEA0(Y1O$9m?_PzqE`(65`=#jp(+Zw#Ic;iRl z8w2bk8Ln&so_Te_>&pJ9>rSB6$iT3cJh5!~;nay&4r*?C`N8||BF|9Af$8qS9@3jP zW01nEN0l>$&{ofxJNE2p3|eS|Y;*DjnY(j()o}Nns%`B@;8} zO0e-h)6xH?CBtPoa~yTF?b=p+;$wN>*{y;kry@cx#@OfosjF!C&?ZYS)?0~G84~NMjhK*DNaC^fx^hglD8rPJE``SUtPB+v^wC}Ar%0wTM! z6Fw%RQY$g^>k<1@NimrCiXwsFCTWQal3%*w`kKQ*1y^dpg+=VUQ7Si4gQG5n&hKj7 zGa`n(CF*?AL|q915aWK2LurjxAOb$;Mzn!6)IZ*-aa3~%z-1-}hZ^HzmqoAXw6!HA zR4HkD-BI+GOyF!m5ENtsK?R~5Y+M2$+u`=au_CI^+T7lE$tpPFYRN}809~nViMpPT zonaS;9f#+=Hc`?$Ln@P1Bpw8Z)_K%pufFTeWpK1XZXfDc82zY-(0Kaz{Hn6UMku^x zmD2{tm?aPcLDW}HADPwF2WGzytCVW`l@fZh?xwKS?gApxc4*}qv)?D3kG~P8;DSY` zzqvICX`sAg7OS-#qaGv){Kyig^8Snd7NbI`;k#H6=KHf!#Hts;vJ}3O({ATnAkg zJ4GT)r!|2Ck17jQADpOHlxU8t4UkFAmMjNYKYQK_%cSVSLKlh*|N7t`;mrI=j=V91 z>K5;|l{Q(J;8cZt z$wb>ZX|W4+br!+z#_|& z5jcSeVZx<^tCoMHuQhC+@SBcD^2)$}+H|m4;9m;cXxuZh$BL(h?kyMV1~Ewm{0sd4 zBerXxm90AdW8#v=oYpx!Ha%-sThF%M>lr1bNmC9U;k=1$D|1zv4*$tSzCX~?$WM=M zUjYi0G$SqSpLcr|a%oki165wtY7H~Zmu=)o z>c65#Z65N3}FdVI!$eLqN#ra`zi4}LRr4C11zHU^V5T$ zZR7GcF4U`G3u4%d4!`@eTqu0Jo^xMo;n`mO(|O-)r|=r_(`Zr6#(Ad|GbmKT2X2EN z`X@=Mf+iR&-7+`gIsV<9eR;VTpS+vr-s$gA7b!#nVM$w4)BPujtu*@MnjN>PTP~TA z)^Ym!Z-edh`;seD2I-L5T!i&cw(RH#gcU!#NOzc+ap^29-{_iIBvF~MW#>h6&e6jd z{%#ovnV?jl6eEwvaigXb?J8j-;uVUx)%g4q$mYGOlW4WrL!fECac(tOd`>2o0n99{ z@lLzF3GFaRg1eQ=Rxg9P-%KsBH`yVW4eQiLM?UGzEaqhs|p(P3Zc)o6g!Td;-eUpJ%nOky^Jdr8+?|u>FI)(0hnq@_d0$q?$Sw zZo>&$8tX=0xtzJKliqM%c978~6@q4jwTPEs@P0hI|Ib2bfJ+NMBt}>>nMj4Gt#osU z0%wr+f@$bG&_>&jbxoW|*a9j}hW3EK=Xm>3BpN zP%G8P&@5%^L&g7C#7y<^2z7J4)cLqwS7hxH+Z){qmX5Dq!?zM?nr>=8ehhwj6>!1A zZAJQ6D*FD%^%mk1Nj=A#4`TnLe-?kD>%ZX;&kAO@ZweCgT*e(Nfoe1J&}vQ7Q!3D+ zrj?U2NS_R$qOns0(Q+>vJ~B;zi%-4N9mdOpLV3Pv!858e{Cd^&kr`)UfqhqRe{TSjLf=459$3W}-7epqp-n1Bc)U21QUpC27x4<+6Oof)p#b0j zAqyVdIB%)I9UNYi?WW3>!=yC zGEp2GLhO5{k}GXh7aKiY}D|5$W8HvIKaj1wq(tPdC{Mg9*n0_5Muk_u`!}H4H*+pV$4l1K^i61R{lwV z>``O&=*;I+3|7cHP2l6)5K1on@`AT!)4ohx9&%bStjqTS((E$0n78J!3!?W>gj;Sl z;@eBZwq;d{jmDYL0p)o@t;CoG9nhmM(VkNDsOjpYYxVVuP9oC*gN;A?ogJm}y4y)3 z%fXj{98&><|Xz;hu0(J zeumwAg#>%etcG? zqY0u(`k^Q8%rY+Oy!_MV039!uXoHiNX_(_@C2nOlxHQc!*TveDO?FBBX*0@6_!k1h zTt0TDs-o~W++~y7xB3Kn%`D8QzMv*C*sjbQCW?Vs%5E6g0X~mn5{`StcZx9h_bHA1 z{*aC5Ccgy`rbk=+ea;kDa!4Oxv1xc!Ic-u;Z`9(sFTs?x zW+rJlA|N=-%`*CyPlqNPB#zFYebG5>pnc4msbYQl(H}*rhM2?|6z9#Dvc&u450I&< zdM~$&4!m?=IjOZsYVpd;Kq-Tr(`3>lE0CuZKdT9D$?(isJc?}Rw((%w$wTf|JwA;R zB)h!6-RbF2&R=)BnNBsXadhxZz`j?VRKztlt~6HsB?E;g<_cwlJbQEpNt@98`;5rv z2dfYJBem32|Lo6lN^(l`)Pu|%olJo@o-{iL=@$jwB~Q(RD$8bgc6W$2&s@V~zsPd{ z5%%3(%Ehl-O*Y!hGGChTQ!4D3vJ@JNc)QyI`hRL6Fw-bepxX&M~3-+4+~4APTZRjsh1Vp-wHK< z>zUM#12GrKA!H<_($$)h*dXqrZ-$i_bcPE@TcLv8{TQ(D*s#JQdY&6QBnlC=yNArU zE`iGRl%Fun;NuZ8x|5|%Ya(2mN0vOgb(Ec8svPw!BD9GMdNhW)#iRbIY6B3xu$XID zv#PC4enWuv-Z)KhzdXRf40XorI1gNdM5bS&ytM8u|2P|4TC9~LDfVMVdQaQ7I8;;g z>g;nx-;?Pp{{JihE@UmgZK&5;55^UarOrg z((^uG+}TUpekIR#ad)Jh=9a^1vwX(lzxvm1v60I=lctd}cEWPqLEytHGX^IkC;8&^ z^uPQLn7ci5u5KVW>^ZmoYh{Sb8)$M4-Dmuo^r5JIx$@rynUf}?H%g3&289r{WkFKj zx*G@Z!zTwU5ui1dQ#}arWy&wGUb?y$n zUfE8Mt)18$Ps8;43V++F;4J)F@Vh}%(&_V%fe1sF@w88D{UVnhpsFmAOIRGrD&x)U zVkuyctDNracJ?TbYA&+Wh__;i@e*qEo{3K9*A(@f$lU zNu1N!bihqKQ5e=Y-+H>F=T8J>^0!i1K{{27mYM##GY!2xODrohc$J=8KlCtBC)q-X`8jo@SNDcX zO)PB5I%(l!h)}(5)~|j`m-LJOJ4aThvL5ctk!tlAZzc^Uso`vs@-$bNIlDlL8TT*sXRoQv^EoT2ufEav_NLTi_%DHy zd7o6NQw}m`hRx8?pk7WFiytFNHYuX3T;`4^?^SLk3HdS@EMILG=gx$l4FbF;~Yume~_ zzpLTwTDKtJ-uyjbY7;afg0l0O-0Os4Lo5+bX|}=r%j|Zg5qum>u}c?TuzG)1j=ldX z*j1G+(yT=~TA%TGF`~Evana*3-UtfWCj6un6)jC8)~&IvHsa zT_TztJF=q+GyEA|LPhhcBGYgY)&mqeX0B{w7?|<=&gyw5v@5ac z74Gh6nXStd3!(c84^ZUGoHX}{q<^Cr0Ro-E+%1e6lfWbeVXePz)!d@3&VdA4=!XOZ z869GPQoeB&5?xH2m}r*hun|T=PlW)viW9}vJ7URn#hKMtYVrS^bWo*}^~zT;ag-1o z6pj|f;h4uQ^;&NCPyR>w74(XLMA5ubV(|O3WBCRoL0H&e%baO~HSO^$+BO*R_Q*-E z&aZ23Qh?+S)$`UouG|>cF210XRcdbYHA#w78|TAp!+T!$)>AD6WV??P6ydDafJ-sO zM!;ewWe#Kw$v#uu=HMe0e**Dcx8YAmJ6u@5Pl`kj1Ai)9x251xlhG_FmkX}QtTXo zv}YFIExPTW2+`TU8VtkdP|v!auKmvZ=)f4yxSnu<jv^X_(UzIn^7BtmyugHUR~;I6aK`l4Dq^Hn7z$ifMF-;xvqyg~?1nkAXD^Nzw=fWI@kk(V zO!?;Ut1one9w}=L1uub`O`G^QK++bsu?0oxB`-V0u7)Nvy?1&(tFWsM$7eBby+u2) zKL#euRa9}OI#Z?sv7n8%T$O0gVd+DF%{uY3CPCmc8i|IfsWcnhW*VCB@?x_-ZmHC? zn(FX((FZ0UQp^?|EUEl5s)K{Imef($RFflUNqH&e^w%FnKEjj{4hz@ZcG#$}b~YYP z6E`$){+MCjxDAwpOa*XAe&g)Q-iWBO$(su}Uub)yGF(lK+5G^B=Xa;AxKHQjF{j^&a7SYnizcp1B93iABi>;=&Y z0NQNT7`|jqSoP;&$8h?0><_jB3-MZ5pY(aGx_?-GC=9=l@3T|Sv6H=V>aW~pS|_zZ zV)fyaV*AIrt!W79Ibq1NyfmhT%3p+EKc{$>fPeV8h(2k${31n}jd9w^G4pe_lecq; zL?mdD2w`v%%dLt({OejMTBB(wRRwd{cUwmByHIVMx^8C<9zL0Dr;Nha_ffnW>+aTL zCv7U`60YAjIz>qtB$P4_Jk6@BE>oa-CBrAQ8mr3)S1B=Fz&)b7dL!OwUbEv_mzm1^ zcg6vK#dw||coq#4^OR36t1pZNIg4y##I4dxQSZ|rN@(@y&hhg>>d)dv9C)nyij)sh zr1iyciTi?v=8}$gswLWj*FDLa$I_S+4Ue$%Kl?e~pOwf%ykALi%hce^vW#94qEP6^ zMBEgde=yFHCD=rUA46qy@e+MXL^G1d0xEIy1->;LZoA_e;G#Z*hyO(y9cclT2lJOZ|$eTBIbe#CfumiagE-N;&iH3drioYsBl{5*EAew)oa6T z4YKCG`gIHT0Qa_mD4KsgB~qXABidcNT5X(zzu^~msicpFg>Nw`y#mJHBn)R+qIac_sMHw9C6UNP}5rDi)coSd3;?tSqr(?uo{kwf_7!w3BS?Z`hQ4w$27{QitN6;U+mk5>PY!f#2h)#ruy~x}K!@y=xhiU@xr#Cx<7g3GH z%L;fz>&f#AM&iGra4eh1%A~B$Z_&l2{Jh1tPb=?y9%$7wb*U~BhK>M(v>~ad67WUWsmo zX_KIG$S+2c;Tov2X2EFf0lVDC{a3tI3QUS0Vv9u@kZr5%wQpD=oqDocMH-9|p6rct z$gdT93>te<`W_^o8Evk$kpJyB9w+5p!8hqp`o8@fnGAFlUj$P{iRn_iWLj1rt{*#` z)iaK3W1WKXkD?!>&50QYPm6R1mYS~%TK&?PZy1cEHM z>pBQ$p+s@7(r;gzt&N&1yLF<4LsKTLT<(CBqgSv1?=$mg%oW?qo>4_m z#E?6SUO)>ZHrtnZ4{VaSyfjc4B}u8jT9@p#Zn}U@_mcm!(^d&jNS7D0;VOvHSX)=I zl1#~VA(6VQp58<@Qao#AxE_PX5oW(JkQ8<^kLCElh88~+P^;QhdM<(h_|OESSGMYG*iG1i+wGsp@Ku0qZ_r5_mQb;!S&S!M-XvOulbL-PaJEL;LyZz` z3Lh5-u{56-c~(%M#&eP~{T4FN-lq{|3Vh}T-yEB7*(?=DLDX;T1#Kr`CTm?IIsfW& z`9^%%XTmYVgWsJgo=mnH($|XTTKuLq9Tty4)-<@2x2^6r1ImSw%|A`1lCM5o6x1}2 zOcAOAMeO#2Ux}ul%Pig}vx%^Yd#3o6)|2jL%sHnc^ z?~jCnfbaK$>-v;*7M?7 z|5yKad)wvx z_!c+K;gY@EaVu8bc!{f$^NqN2Dronwov1~by-1^>#v-cdzMNhNkazgwZdWK6Y@yf+ z)JSGTfUT$`ga!nG&CbTHs-C+HG}sz-(iPU>$H~F#U+HpCe63Xv$*Hk&B9F6r5jg%e zc>lF<4jNGo<#Ib+$LQ>c#gpl_oGJ}Hc|*$n?xOeV*d0~FE_N6+o{DR#8iN^h2sTZP zA>bV7lKtb_o=Pt?3kXWy@%g(fcF?62Fibm7s}-WJE*)ept7|~{!naTQ$ICV^3$uCI z1Zn`-EW9JV83cZ+-Jy)tULR|6=4tdcVAg7-?L4nb>KV$zB?;^S1O%O z%4TE1x=demRS}6Z&k{N)-++KVJI-iGX=Gnr%K}z{d+7u#!>1Si&Xq!3Vj z5r5h`mVKa1Ad!3k-1?}UZLFdb9N1}o~cp3S0kGP-6*b`uow>B zRJzyOglAV>0<36LsJ#n8{wobbHJH_xItgZ8GDG9=Joo1q7d6}e20!gqaWWUbDi6w| z@N5^H_dc3UawM_vfQUyz@~azp0l|pdH0U*An?p_1@ivc1YrQkx5S4&Do@x#})Ny}X zQ$YRYlg^gZVY=>My(*hmt%Ni02N}?&RZHO|HZ$nFGN-hTpI6_)S@VM=Rm??JIQxt9 z05Iy;;J&!~{AB3>EPj%9B|D8#c+TR-lgs+R3yCPcJtbD(k%CaV$pdschUCJ7E%NQP zdonWi>A-Q?TdT|O63qsiTTIuEin0U8)ow?wG!EAMOUF<->zc?!6_qw4>;bhh)k1W< z|CaRu()`kj2_s^3(2N3-&rYdW)s_;Xt(ESfQuRYay$VUEd|;N%J0}s}nkY#4(b1UpNft%ZQ^yOf#GBTZY9y*eX7SA3_5}BZaj1hK z$Nd}uzUccjRzZeQpV<-6jdDZZQJTjw@J0Nnan2UK5oCK_RMa}YTRdGzm=zV>r!p3* z6a-&(?7?ULt*Qod(Y~8Z|GlF(w%)d0UMsyjyYDl4w|X-&Cnw$eFRtfSeXirn&sABJ za11?Csjc9}n=sQu$D6^k#L zz-#pS1wCWs&%Z;Vr6CEy>4?3x%}pX)B(y_nu(l~>g?UT`BB?JG>Q+#@kO_PFcAdlb zuusDE!8ai1rTI+wrFQA`o9cGAc#c!`rz+h2)a`%U==nu#ndLhYr3 zAtQ(TS+b_ftrF{Tl!0Y4i_1HO$B(0Kw1!;@eJf@hA;J2P6(9qYpmg3uvDo#N!)Sc$ zG8Rg{0%izN8+p5&Yy?eW(3cWu9aCo6iF}C#Rv|nlnKRL^> z8|VH9C#zef>R_dwz{+lv78J&#p@YE7tP9s`sz7+XpyNUZ1}l>^dj@k3%Kpyp3}VH5 z9$@+@*88E;`hsrKv)lskrRhfQPvjHOGf4I#;{stRIe zcqKE|`(H=q_yi0p5<3>;I+&1!ha4~ind8bC!=1l2H*{Laq{yvEQVVG&?ui0}u!Ohb;(gi_ ztveUT%ANcQlhkUIXoOC8X}_m{3NKuPCy+v5HbV7GOtPm#{1>U#s=ld*xp@}DQ@M*0BwwPVTzPlV15N?|;R*$A% zm2LwDhi?RmUyW>2#>?mDFT=Us@sjKB3%pD+)x7-4r0$y;Xp7?XV0TD%yaqUk_j=sR zBgKiz8+dUrM~vld4#|f4X>~L=J_WNP$udUU*l*hbcISSh0Vg$Ay#8iWt0gBg#Y-|J zN8WE7FuJdkqtgwN-WD%vuSPl`YTB|7A%A6&ZmU+Zz3l8(`WFY|Y(BobO0zC8aFc7z zd=|09gav(V5AG^wxvZMGD>o4(r-k23i(-jQCkP!?>*~|jLj~^7=L+L+Vb~c1jdmh? zq~533`}kNC3N`3qxR@08NI<-^%S&*$WA%P0u?CVpc1bSrCBrWt#fxwt$L*$Ur#jdS_NTa= zr3@iL2m}2bzkH_>%hZDrGmTz+Q|CiY54t3Aml+ye)uWFT)AmDOo`}M!fDKuA<3DUnjEc=VH!rRi1f(}J?Yir(7c?P*H*Eu-Ce$n1xqZDhiWhqn zl{ysFDPAc!!Q`c3JRm~t$!);T)Nej%Q_5_f3ri)8Zd>~@*jNG2{ki?AMey50SI}_h z>Y>E;gjklYT1{wW1}=5W>CZHNVA+b+{!?_2>d9horqh?Agc<3BSX^WmhMWSb%OqU0 z>m!BRKcXnd=H|>#Pm>nonkU99%pP%u(S;gSzGS!?VJk)%w!tGosBzJlHqNQ4IoKi> z8%LS%i}<9iV!m$YU{T;KUTaRl0}wO`)3A4$gNn+>Av`FK(JI63$qWDXF|Kt^e=>DRsu$8B3l4wHZ6opQCgSB}>)Aw66 z_0H2^UA*SMCZd`$nvy`&ZJ!+3ADo^_qhFVfE zuhMArd+jIYIB~%^yg#`t19~0W28ByU4V+!($}Xg^3+cJsX?~3YRl5A1rG&lP^>d7@ zc>(6Q@o}Epi)cn}trk7@^kYVBJe?75rjC7RUx|Ij1BOE1lP$t4es-$`a;}Gy|9wwP z6(?kpQ=UoUWTb`9o^D>})~QO1oqxJ2-9xAd_Za^5wn3-VPggKiMSQuo>~S%3>3LsC zFa$o{81mUEw%XTs?e{FQ3pof54*sOgUnrVc52O_+t?ehl$V9ZoCS~M6pKk9G>)klE@{arC!u+Z1!M7h|8>++LX)epI(UXR?xJs3a zfc>;=eh69UO3oq_YPA09i}&sW0<&nFzT0HcdXqevn6F-r!HA9;5L;9rvK;bC9V2xOlJ|4N%*H8kuC`QzjJ5e;1e`7RK3-#fx){j#7qn3QOs*u9I>$8_O zY}U5ODFM;Wa*YDqFIl`37)PYIl%_cs;=zzUI9RD>W-loggYT3t)B{p;$MU~^wHHl7 z{D9RaTO1-^l9~!l=pOPG1;KCB?6gDP4$*sV>C6(DGTaf#*DCD^;@sb+GLv-K|J}9UildKO@O6tx}Q)pZ* zwk$oEHP|hZIeVKkMM4N(9-0fhx%x^2tB5-%ep#Bx0qr@}P-tTEtI!&$*5<8PXn z67Sfj>8LJ&YH)O@!WuLC{RP5{1htCoqT3x@2CtG-HX+IxY9F! z4+J_SjiQaBgy}*|!;(G~*9iSCX@^y3zsr3bJsb+b<}T+J)6vfzb(4 z#SCg_XyAE^jt&-?r%ibjp&Ev@R&hd!A)$Om6%*H27m7(MK%V|*fIb`H5o)NR2m%F# zDXVZHf1g{cev2$Psv;{t{{yyQN$6R2N%I3h$h-t}lNGL$RUA)fOWG?w0za0VB9~_^ zcKSjk37E7z9|a!Z@dWk86Tt24>^j>})(a>$M3r|vtk}<3;5$0 zW$D1Rwb@s|DiQG#k__A*jeUU0aaRj{%b#B+{ z4Fch?s46MwYk7NnPXq6;_5d?J{lCCaVw(rlSAhULm1U-=iFQ)V+tc%p(`}?eqzwHB zdIca{T->i@@}3a4Is+28tE+2xXm9Lh-Nr`)gBEgrjU-!6(IBFSf_Ms;47DG`K)<$2 zY6zf7;kCc;bKcDhpg}X++)C&@Z**IZKcS_kujvUfa-a~YK2*p35d85Yqwh+pU0G%2 z<0Y+bki2B_ZS+Ec_O7m^;E*6F*B4i zdgEH*pWDJxr^c%9f&%sb^(Rv7Tyk4u`q$(t%Rcpcn@BjAe1(%%sv;LP?`TwTNqP+bEl=h&{im|$r Q{5EP;n5I$%)Z*R$0iBHeZ~y=R literal 0 HcmV?d00001 diff --git a/docs/web/static/assets/images/integrations/lerobot-foxglove-droid.png b/docs/web/static/assets/images/integrations/lerobot-foxglove-droid.png new file mode 100644 index 0000000000000000000000000000000000000000..57c370f831b8ada9bf03d607f273f7dc5948e180 GIT binary patch literal 572468 zcmZs@W0WM}wzXU6vbt<{*|u%l=(4(Ob=kIU+qP}nHg5Lb-x>FOWMByh z=qHebuz<2_#)TI|in7SklT7CP!9Y*UuTWo*yuGj#)L$VrVPP8b!VxLRfpJ2KLjA@Xgnq-&!i0JUj|^&+CsqT^p5@i2-@fQ6vn?OZ{MW)}hJ)5)3-#F7`@zf#dF9GCbmT!SipzZ(O_&@LERF(u; z{q`M=*AFZ*pS>CRg}eWjE0tz%;F|MLOcznqa?eAYk4Pl43`uYWQpQT+X@G2E9V zj3{d-UJ7dYquO-J$%O6y^Ck1&3X+_7-?n1eXGPkcAfM3wzS9d-v0tcyytV4m5Iulj z87xtd4gG1{AE!%QggHV+SL_+x@Fl54+66`NYDdu;df8>E8DY8ksd##!FD=nuc%y$p zn%#8D#rvv8E&^hmWrv&f?J<7ok4;HQ_}g1*MEim$a_&?sLikO1cmFkq(2zSdpG2n6 zt!ONxkdm@BX1bu0ywJs|K-kuH8=CUc z>DKcFrHWbS@jr*~6O&@`E){wmeu!vo>Ih1*6Xe-tT*Od+@UPF|wn$IO#D^tgY7dhu zefnhFuU(jA#oGgPyApCq%5_`;uB?%|2;&#yJpJi-Jx7|7cv&AJLnC&l2BVTMh%2G_ zQtY{}c#mAp&(xCg+~k?YQfL+Yg8vSwPpJZu5GnE;z77y+-ExncQ($&rE?}&0qj6bP zr3A>Imdsdwe(|Qhz(J{Wj_m^xaXHB(CUT1BeI)dDTtFGW{*9k`LPYFHoz=;Jgy|)+ z+l4>x^zY@1yu_v8v<5J94Q3Ybjss1a=<7!ty`1RN-HT15)Je51ne>a^D=M9wOU0jB zQ03-o*a1QCa*CA>_L6B=)Y-w3NSUjOug0v*CP_>s7ixi)jfu6*1G3rS3%8<4b; zf{l@q-&mtr`BI-r)0Sz?jme^!v%uijtA8>St@)p`ra1pfsOS8FjIi$gW&22=_?t(v zGbMNPzDgDKZDjF3^Uf&(a)LOe$$5#qBB~PC?}Ubsx@jSvF{vpxg=!&J(Y2U1d|#@{ zXd+_O_$8q^=J1r5H07Y$N5~U90(EduQxbQKn5ACwi#8_CbYmznLrIYgf?Im3`xa~N zn;|?quhdxZ)cEZDpo4r;GJjr)DjSNTvH7KNN?ro*i=RG7nAh4yf`Nd@XpI`ww@NB0-bJ7*c23Xu2uE$@~S8Z5At}& zME>7BRK~^>alytyg#|M%Dgp(PwTs~CE44Yi=zlCZUYTzxFR>d6Pux6YP|e?mdYXHb zx?u+e#L!-4y$gz~%{#RnsREqT;;`kq!<8eTuA^C1ZAjtbuw`ruhBG`#i6H(Gk+m{X z8du#&u-38Qsg58C6x^Zvzl2bvKD1{`Wzevh-4Y7DlC_#^CnO2JE>~pyw{!n2qyOlzs9zna6IS5HLtt_xO?=6%%2anh2$ic}-I$v* zY+hGD%Q0ccK|>z!EKrCERdjH0(A31r3Kq-_3IhMIXw-~P;b8feRUnt@Uy;Q-m#L7_ znkNPh(?4|Y)J+J?yTz50xBM8$XpRS~T~?9QSycNsz8%ekSxbK0>dStT0IL_L&WO;z zZrNnaUt5z_3$2NBr6fogp010mOUVvAM9Z>YH*5?9c*twlBI8{e(lo$q*@>e{6b_Jz zydRemB6D^Hz9C)qHI8uu_i07%nOP(|ciUi?P(}(I3ROrZKLk%k2>aaJF30)U^U zHccv%Rc*_S%3cg0(#3broQ99Wa@h>jASQ1#EVcYS)VJxEMe z84a2a+UHm~?}ASM6vU={`K8*-FAIivh9;o+9|}8$j$Jvu{vz(A@yk}m?V-=}rT!C2 z3mYTBB!!{EQsZ?tNOh-h(AZjodPAM6fE#mncLipf+%@ym~q37lH#s>mn7n(g#K}%0e<2%>P8* zYEu`b?Ga>82`t=|)`oyAWQ|%*pviQN@2Ks7r5;ew8WJ9@aun4N)<#0o zqmO?Za)l79@bT8<(vn^@R15&B#z2@7iM^;VL%GpsR8tP@Wi-SNXuxDd3c==2$(mwu zFepQpZV+tHDL{js!wD-RrLG63^y$kbnyaVHh;9fZCEab#QSiZw)u@qR5DoNv`$c>i z%S-7d$S7vzYm%E#)AyT1D@LgVRWs-53B{u#c7flFHMZG07qY=voxqDi6xFXpkw6UC zI3g*FU3Uzg_MZ9#884mqmrr#fxm36y&D?GM6*GR;7F$lL__{)WIr)fiC8KRfLTsU; zEu@7Z39e2dFDfj~T-%J74JDj7ECmlZIxkbcllVUCN@xX3o>?WLqD_3FRlF&sa~}NZ z2@HnB5Mq`SLnw4`LOR}`{rbM8zXznt@*1qI=F-U zzI_FE_rDS?D6vd+S0ifm=`rAg6}U`HO-u~rxsp$>!b6t#h5wCyEBU8-2|fLtJHoRI>ZCT7)43udg<8|lq13$`pS&ZGj;8Khyt zwZrT;+Il4o>Ljxm&L~oCOLZ)IL&ipguHku_p(6d7Olf&UX;H}`aSY~P&dg2QEhDBeT}q$(a_Sdgt!SK4ejW{IHE*IF2svqZPz zF}x%vAY|8^F}dK1$j>H31RJLv3<0MnM1m6^ogWMt7jxBR+Nj(?C7&*|xinU%Ryei8 zuHOcU0zVjX=M;;)ikICYe<~@3kdJH$L&vuNV7Gq)SEoyLP+NYet&4$e1ixZVpUlMa z)1Z^#Of1@6R`$_lx?|)6*AZ zJKUDe+S=RB=dJUSEbrzABs1fGYV`;mom zv?J|x$qgFxI313TbEn^o=G+>V4jqQ{SbzP1R!xvu6p%i*$o(qfmNquDQ&?t>tr^?d z+c)vxkk=KYNr~rEcOBa|{mXW@4f>;dE}VBOIJk@9@mX%3)@^-GtI*l3R$>y98-2dL z|4trCJBaiN*mq^;$j48_gRzmR-)>s{>R%^JQ$TaAO_|KdGsv9|r}S<}yFBsY!n^cJe zX}}TZ;hh2B9F3UAM!?rb!9YPoByc=QRZWd7g&HkhCsIBe*}aVs#k}v=Zzj!8-E3l} zzeoAMO-xMK8;goan};C?HuwG<9~=Y-F&q%wYF=-33K6<{$Kgpwiu!A4Xuvr+k#C~I z6YvzsHGQ636_v%tlkJ8;C{9k0&nOR?Nc4N69|-;1;LIsV%yssIdJky+2Oj2gv<9D10C%uDO5S-Cqc}4ygw|i2q>$ z_fuTeDPEZZ%%XV)4JPD8{>aG!;bRJV>>+9HLNpI8@EopiUp-9dB<;U43Me}w{3BQ` zg+x|wcKfNQEPlu$1p;|Hd9*e(H2C9rYG|YqaEK`Wv1l&t$!5|p7OBOOCa1c%%@vJo zz#ppY&?!IRSRstN|W*48w1p#$`E zW}WX(UT<&bS8eCCEC-@`ac;m~{E{3~)-d;8Q2=Y+;_5ok=nwvs{v z$M=ErOde0CbPKAvs8*^lZ@F~j`GqAcy7B#lvPzI&$YAw@u$@;mE3>9^jMgJeNQ7;e z80dilGE(3a1p_}6eoB0sZ%z`TndHNP@VEBr%SV;AwzfVUk%sXZ70^MJP@AfRbh@mJ z>^5(?pZBZrT|9&DK@_^?7lpwB`n0AUop`fea!4%ph=deFf$~>wb2m3PgGT7r_r62; zVm|~En7UOniyK!@w5^$Lz3<8OXMtV^1z2}bTcqDC7PXpEQc}@)>X42W3|s_oB1*AZ z@$G(Q=VlnEBE9mOUOkEN(M@O*1xvg7Kd4Y0brP}?)74Z|ej~9zIFJwsxufx|IzZjy zH8@Gt<9jZFha}8J*70C%Y+s0WGh!KG$cVwqP|?yhrxKZQITRs!@hdU)gyt~|sfxmw zvZj_%S!8%RaxLLluYM?yq(*ZV}S4Taf`_`1p#Ct=CF=w(nd-9 zIDO#F<|T_Z`#`vWM$in&VqO26=Xrx^#zsD5rr7HZWz()7PF??JGO4>&7$#mzfOY;N z6RkiS7y#YCr;fye%k&D)CmtE@0=Ecna98-&S~Y4|_b5{{!0bdlVC2DFxl=0|>DJk@ zx!&w-w!1Jb!+S!U3|hPZ=0u;J()O6*(b%n-nVixCW*=1(lLYw~!3}cJmQiWeEy3QO zshEoxy0GQOY4sSw6JV1NX~Pki^*4T6Xw>RE$;8V#E}LT2G@rM__@8ylCiTETMpuwv zAnIwv$o8^AOF*4rVPRO<*eW8VKh;p>5oLZQu}Kq|X1Ns&5_mq$iU|e5uC}|-sUE1? zJ!5lX0DTSQN5PHdPOEu$8IQ(+>jBMNJ*8h`u-8BoRfq>Lr6YXYtxr49c47B$jT>ur zxZVyhks8dcc7Bc*XM4Lp$`y{_IH0k^1~)`JM1<9SW_#X^#>?@JN>{|J{~5-GSb6Q~ z3w(dNtY;4ulOK`Ow`0c$ScwIfOWS~Wdpsw*8OTMCh;6dNT&*JO$%+y6ClsKjQmfMb zT!gspxRuRVv*~`nY6taT6(ST_zyNmQ05dyG*@l77C&c3shNJq?pp>2Q_V%VE$Mcx`yw!Ty zv|d(zrY^>a71{p=2daOs>h(B)EcfEyK#VE=g#^6oot@l(1?`XLZhMJW$ z9a=j%3k(XL!C>&#;l?Db{c?JI<$hQwH@b>J{0Cpr*O#QUr3GVR+isKPBsH4n&80(8 zWlQ|c)SL7GJd}`x7x=rw0N#$a-{7y649IS;Sro(;|69fbEcfV$9UK<(iC_0-Alk=q zIn}J%WG5p)qNSn2au}E(4J2%%|&~2}09j|xHrJ(w zp`sz4^={XvRZ|}=`~g?J2R;N?JbH4h`3fY1>N>||uzFhXh9G9zmL30b+IC2{s;|3j zbySsv<+|I#bw8(nu=vX=U=%YfE>%5uw&vg`n8Nv*7A@34PL2E11(XxVpFQCNUsRZO z=@b1AKP3tl9@XON&L^xpU?!X9cb9Fjx4|-?@~HZ0-gG%(wL^FkcX2VbYGswd587Ne z(}|Qn>fHjAV$P9ZviyU!b^db)Cu3n?=Vy@aTqOVDe%JDbqalT!^7Lhxs~lhYk(&mN z%?qd~DEc~4Bv$Sb`a5G~Z4C_(7~3;*8{{R4mDi4Web+oj#aqb*hD_-fz;> zg@^pS(;%o&W2MzhIh?zMBcC@LGcS)oy_;w~EBJ0Lx7Ku9*GGxz7PwBh*HlRP#)08)ktnG5q{YP4By{j6ZFz25{UV;( z=#i0`%c4zUzCjkUwrp_)Cne>%uIuSyq*fCQ;~#10UU95! zH*+~y!JUl!(luXIC4mmHtkaNsRs$y<0I3ibX&9P!iO;z3P8(o>v|2ZX_o?LNDkF;9D9_}t%f zQc1M0L_Cv!1{<57M(|yaFA)rQ{=7bz7m1qdiesx%NPIKDWE7WY;YNE&N?IQt9$o}egkQ>qSU|{d zb2FWn{Xij7C{UrxVQjP(!PkR^sLajHwU?i^wn`te|G65yO7`T2s%`FDiGLvwve>?nd^?-By-Wd} zOZ2xFW>Tw^p61=%IGs;-nblAPrkXYnUX1-?GT*kxbtg@hzJbB6SM=8VZZN+0!ySZd zG4lE8u4g`>0iEY22*ihtpIJy@qRMPDedDn^S$gx^W{Ah6&0=C+qS>#-Qx^_ z{;QE6=_)CM^yAXJ=fYPL$hGd?U$3U}$z)sFUvKBt2$+lqfa(a|ymK~A*KOSUe0Jvh z!StCh6p8J!pdiNcFe8Mx6aDc45LB;=YI-`iZ^1n74=tZh>%icYROt-aPnYY<$M?Y3 z!1gbn3Kp{Hx7?CO7$Byqs;Yw8Dbnwc*FKXh%NcHSerHiAFovyv-4{jkeZBPSb(fZu_{IQ_(sn+~?e+(U_r>aY z-VUD0B_$*!feZGfFc_I+^4&Jf%K{nzjV{mE;cd@AES|>&rT!qedI)UMXgsg44+#0p zjEszE-Z#kC9Nl9zKkqatHxu=LFk#D z9gbM9G3bBSqtk15t}I?-a=uszr)`7$P)<(Re|Ia!b6a2-{!qUN7*foTJus!0w8(E(2|tW&RCs#)}JBLDUaK`eo~xh^q^9;|NGWy9wXAKHN; z%dp$6&^YlxE|UAPq4~Ao(f##iDKUxHFxYyWrKPQnW35Umo8db6xSY4x^?LFb0Ma^| za`Cq1_|AnFK5KwGo2^#wX2%k{KkmZ$_}%vpO3AVurZ`M9xSc-Rbh`9a1O$MCklH2} zN`H`>6v6R_dwxBJRd>CO9h0!VW74Q5kU$|ugnzz2=TD1+m)dso0)*Sd*qHl6ubP4Y zWIPTueaxpl36da{k-j%T0-ZdaDCfoqU)$CY1Z&xLqRM6YIP$)=79qm40u&Qq)cV+M zwE$WawHutR&fPT%^3K*JAx?fDG^Y{(A2ZQXduYt%0N{^#?gBmdoyP zyFdEy2HOGdOi=HbJOZ4KEwxQ1lW8n}9sMQO|Az&zR1Vu2I1 zVQ%>!s8y)f8V$og__1w!B5%U_3x>La8ChRv;g*Qw7d!8Tl6gNpHt*OCgdmDPy&h+4 zQKLaxFO(?ggNu;EV|7b05dr`5?HZe%bUlcked|rP_2>Br{b+R6pSU_|`@3Da{9n&* zTbAD!i6j*%Veq;O1Ps_~QrkcGVnxwUN*nh9!qpe;=8Z?aod{x&gzS@7*~&aOI6`{h zApbL0D`Z{aPRC?wkSs~`CnSgA5Cvtip#bC-kS|sFIL0(NCkxT^HCisHK7h628umwv zoNU%NTg@Gu20xyL&Mr1j?}Cq-qij=StyIf-ci-_O20!B14F)E2zw@yf)q31#Hp^vs zzqMaiN8L%bv_-ji{GEE}5(=hNy-dbE7o6k}!*eUBZEf}3Y>T1E98aFVb5GIE{XNYc zad@{9Zv)EOvL9RQi*YzMhUaCkr}MPYWW6rS>$Y(U=*Z?f<+R-n6V21!8%CLYK2D3% z(WzTr=H`!doeHZ>TAN!(FX*wYMZ@Pa)|pJV)w;Wy_f+(zQp%4vYkZz<0rK_pd8?Q4 z?Fa%N)K}Z?{t?b;@e!L9m%(hNl__Y;{XJq2$zZL)d^nnRVD7c?_&fGG&i{)(=ds88 zwY=-gRO8krG`w)$Lo)*Jhx+bdHx8FOpvu;hPW^bva9h88W*=ulxX z>oSY(hsa<%zAL`!_L$D%VKSBD@Oab1^SRI>s5(EA`S`d$HkmFHrE7az>vsPrWP#}8 z_nj}+ZZKWWigk(1q&Mj6^RV%_j&C+rx#Fw&J{XM$Cf4(LwRt#`qU&lXYBRZ%!ww0y z6DLG0`wcqGWq&uK0!<5G4}SvStXx^}n1d zPR@vCinSwDPplmejuWVXM+IVfOo^)&Ju;Ln>=%xb5`#Wn|z0 zf$q@qkLBg%ZFPE7Yq!?5wYB+F`|Z~Fi;#6~JI>3Xh5xqwv!5gIx2p9BtM1R@{Y@5+ z#~xY7q1{7&8A>Y)D=V}==FZP~xS^-7&-Ys4p|Gd(>h3Ap6OW79VYKVj2qIr*pb0@; ze4yhp7A;CjN=97F`=d!E!>(MR;H1RF-Fb_~I;x$yxj9e59kA)OM$6?&t>Q#qR|`SzZ*?s6>}N*s+BnF>=4jVPqo%HoGEM=6+o2DNEW!WdV53@m zpUsXDVia_pA2NR^BVb4{KPLgsN#WO!qcjmXb|g6n(_I!%Bc_-!3JS`~Qs*b{N-XquLT10v_kYzLmg@nM%|6a_HK;g%r#SyMGs;Fz9G${bGhA zaN*5?fE*~^qD5POo#9)&RMby_V9Rme{;-g-5#Bk`F``8D&%?O2@$%wvhg|8`qW-Xt z(EUL&Gczh(N(|SPLu6J55bKyetX#t&!R2T0N8>%L9kE{<4%30sIT{M&9J123#r)yZ zZB|$-UC*jcxZ?{PG*dT5gR z{r+=L$p}O~9*5CGC!l>`Ep}QgzGj%GJwk)EmPTLRxSNj!RJ1koVm}gCBG_r~Pxt)k zZ2*KlDS$zr0H4sUH-XDaP*LV*?+=O^Bv-#ZOeU}G=)hU5Mlb_75-HFC?=B39@LPDo zdb6keKcPo5lA^{{!Y%!f7MM@kFJ%>^2SiJt*samw2Yod)JV(hG(N5 zIc|1?M_#(s4*|NBR#vmV-E2yiOvA?49zDKuqBrAWJ&2HE_=KKp*tQ$rJe^p}$F1r(E>g>g60g>J#SX$izslD1 zr*&I>;evd(ao`g#wmovv${!b0FRR03adJ4cU!Y=4)|+(vfYfv~_YlB`9`T+87An+P zKB!XqffqAPs4(o+y>GMba^$9{CM@rmFKH;iHk{BNwl&+<=hQFHQumiOct_QA+lH+U zD2=WnwlG!WTRRGrqlTQX*R)sZ3v9Q$C~YGLV9StDz&N^1o$IS}3mjc^yx_>L%q>b# zT}k-p#@8<*Me;NJ#O?=~QSIYZ@=49&P83lYPy|8K@&w$wndNp;8RiUCK4=AM2Z%H$ zemA3lgD#m3U>SY!^!FQ z_m@}rv&x7<*QgGY$wbP$Y)qShS}!QX)mr;-?9p0R{(?SZ8thTp+1lxRF#;~< z!;ocF2cUb*_IlFLp9Q)O<@S5fo2TN?vcgit6kM~HurHWqIn`t>U znG|}1%^|qD_R*g7C|sVWy>Js{l?w-tj<`{7#}`Oy5b$G8K&r)S765)y9H;i9c`j_s z(S9iuqH}zsn=1S_|IkJz5u*26j>+u&PMe)0J73>v50cng1rPQ8N3spZiJIp%pg8$C zjy_|-v3IUsUib2ad%(W+;ILmsMWw{Z-Mwx75_}Jr!BE)QnYR72rKScQsxe-In*ZQz z@(Nz6`9HDpdBUGT8s_Gw8m1B8o^Kc7(*R3><0&Q7H=l~nYxMXYQ`v2QD6*W^n}&wQ zdTTLxI)mdrG0CMv*Oq|4s#8HI7a*d1o}WA}ewliEe+|LC*HBMQO|hm=iZ9K~#AN$O zXY+a)+iCzHLX8r@_Kr+NF%f$ik)hnBhqkb>>Ds9quWCChqcZtSOt}kcjax2)f-*#J zjP;c>K~fD1Tz28i1YkMdoyc5m0zX_X=Nj&R;B8sY$Lpe`AK+co+U@p1;JNxD!>L>R zWwVPK*m1U%LDuB}__#K$he>eQtOVa|TdttoIgkfNf4HQMo&Sdg6cXM8fRn{+o`^U& z>G}D&!k-~R*2`~er=l^#cQdoH z;=1u?I50i^wz#)MUM?N@Lem)uoWjr`&nSp-f#jD&jE{o@hwI2V-49TH#Pw#|YHFC6 z$iGJ>hWO>x!Q#C@u2fNDB}LU;DI3n?R0CnMY>YI{Tu4@{FH|qRT06jkJ?I@ES&3p=2(%gJlRMbyBV>-yq|d34r>Nz z;v;^^;tBdDz@+Fb^Du{mKc?2=u?W3J&@lH1y#s^H%x%E=1_uWvrtzB|u_MQ*Nq;C2 zK3LI*#$=?Y!(<{BJaY)a12~cA1iJ9Ku%Q7G7Q|qyqEerh8lOD z_uKLV&OApF3W+AVD7v30NcqA@$x}AX&;tT{fOfkRAWMVM@Vuuuj_DIeseANM;T#`Q z1jM4<8oGKTnNyyO%C;q**AMhh&#Ybu4A`G{*;E-s(`m8}{+`~5~#@s)t<0RyWwzEps8}$_9-d3wa@#qONrp!C#Gd!>TOoK%H^W}PTWnGbv z&DFb1iX`JZ?9Av|3*}+lN(~{SZL>>8T-)TrSp|Zb!&qn66eNGad%GX{4KnROHML?q75#S$rGDh5D)^NPUC1)6X*tKYmFLQ-{>pXG%(0o zr5;sqAScJf5m;P-^=tu9J}J8Pod>3=H?u`GK%0ZbU^oD1su(7puGw~yu#b4}Mu;b` zYOoweSe*RZ3-dsR0vp$n`oFXN!o@ZroeT;jQuADtc zMlbAEi@u%K)*AV2*BVy01@nO084tY*`E1u&9hWMw*{sVOIINa+S!|z|cm!Kk4UvQ3 zc?|(cwC#$wr9*p}Z11ULJ#WI$UtcxU@!~zCe;J5rcyOwyXeuE^4pPyl*6z-mdt`eM z01e9xou%d7-GmKW(KxlN8T&`b*I*$w$nM$wk*?2irb`sQhU3wS-!pfMaEOIK;p~N? z9Q%HsUh^WerV#ox#_N3bHi}wV=f$>t7L$oKCpyr@g;G!?^@Qfrs4Pjji=NMjvXZ6q z!vWmtlXm>Uob%O|f{s$7#Uf=-hm^@S_zdG?z^$0+apgGW12&G=kI6oY$JmKD(dfYH z&8DZ$Idfv#wu`t#Tc2&J{OJHASzqN!@bUtQpOA0UYuVjt?B*XL^G7JQm92JPp@G4} z&PkB7Ay|ZL_0Va84`R$krC1DL`#II~4->G&*h7O}sS39&-f}g(UA?0G1%jBEVz3HZMfu=ibdn6xJD$1iZ=v z+d0REx026k-F>y{CMooAp;TnO`iA{5_F-AA2grt?^HowH(WpfBYN+Yxbz}=eW;6ep z05n9UC5Qsb&&dnxxUccwaV&u2kDlf2J)T69n7GJaoVuDccE;0n0!5a^TVD2Yjx5K0 z_F_~7h_5aiLS3!i$M@PVo+3|GR=Hn&+!se;^LZa%ZDOV-S+6h4q%htF?2~yuEdqj* z+%~;VY}{`r`RP73L*n6aRLyQA;ITh_ya|Tpr`Wv~&#Dmu5^_d&Vc$oS{8oR08ZQPk zL^OPHRB7|R-G9}^5KrPMHHb4ydUpCfNkGb=+cJQ5hlAM0FwVmslC0a`Inbtg;w=v^P4oF!%;d1uMnDE(`|2NW+r0uN>~(n|S|qO9 z0c44USmxoCTBGV#Gs>OAu1@cqRW7^^vZdu44<#p>W(`}XXmHi z=z7Y!y6}^5UtZq7=ML^SWC#mVc}$m%g&^;fp7pZopZ-9CK-6ndVmYx{6%6HmIUsiqmuM^tp39bV_Gk;t0dyiKa?Pb>Mw z(y1VxQG0P(7&xIH6GG%2l4@wUXk>4-0KEP0+BDigVgqLqB<7Yeia7n52x|f}E+i3P zCT``3;p5s>tH;O33wrwZM*=pUcoSV``xWxkoW3|;)s)r=@WWFYQoZT)o}nSfhKyXv z7r;OS*djj!v6*YWr@TDyU3Y*hY-Tg(@;B z0su?JBOyI|*#%&hQ6+c(7{W^T`e&~ls!i&)Ii7w#e_sCcK)?6Z6mZxzTI_Zmrg2P}*oykusTL6PLk<5 zA;&OrLiyrQ!lyh>&>&b*(tI{{Vb}-V^hV5zPK7fzA|5I?#fGZM|8_*M7ibtANS*X8 zMJAIKjvTYFAgBdd^~Dm=2_j48`Ag?(AkGSi=v`De+7Gn^Y#77PK)%LExt{{>=ytmA zIxWD!1@QiDw&{Fa^8WPremifY>;AA`Z?YB-66^)yq<7F?LPBxR%X|YUe)+*birFUK#14%D9C{h^%eS_eqH^(;GEK$SrcBN5jdmP1Qxr5IfkLJ*V51Xi9r z2$d4VOzrq7_jhTO(xo$!gvUyaK@6)eepdYqZkaUomO`6fU>c*0G*0oY|9t4)%&x)% zz-?2~RE+YL^)npTi{d>5&?V3J{>T#V&S2pH8?&;07g+v;z1tXHV+NLq*&N~#rzL zLVhSR+7)D~?=>DB*2Tm@n} z_ILMU5g5Ql5yao6y773ds)g|QM-zoenw7R~Wu%pdg&Zp@xW8wG7s2)UfUsE^K`0y4SAR4(&%M z30ymPsnINiEt<)Yu`vcTnES(tUm`0Sy*k$eFm?`+OJRwp0B_)_ua)3eYm@NfJ_%&w5<9V@qv?tiEWSUU^(~ zSOV&tb22iMvW(NC7L{tp%}2PpFDr|x;R|Mjv)+uuRmA-5)y1oe&Gv%>HP#QiGnJM6 z0#`jFBjNcAE*I;Lw={fW=8z8nEXHQD5p;HD{bOkLD~UF6{=?w9Ewa1n^%SB#&{gn` z;jchF2H4@?aJJW5t{4zh+8H*Gx3ikE!KlaX1Pp_~PpO@k(xIQBJEm;M6Ir}0LcgA? zZz5v>j*4L2w*M%}@EL5Aa3#2um(!*cUFY4J<+#cqKZv|JV*YAI;%|^Ch`V0FjWiRk z!w7tkT*$LVqj%e5*>n{69}+!Yi9LKID9jp+KCidyn8y{v*}U0gd}KUGaOQE%Q##ZV zL#a%rX(EgqO~P=mub;40zA`G7mSc1+H`)}UeKh20y(TP_8NxZSlw}$69r>Pfr}M6$ zN9=!|x3J)G-PpxRc}Di`_Ye8mx;*p;@lZ5Do5cJQyUY?rtMOQ8b#pc`#Q31+HFA$~tybw%N4ro9)j@>I=iX^E|smzw)^v zUzC`&?ER^ zlE#yj4QO);lw=vO0wN+{1rjW=$8k+Oq84Wqb-otIT&}ZxXgWP(aIQzkr#EVDj{(L3 zKVzJN>qY2bb>|C+zDo22H92=UNrZQcm(J)>HXeMi4X7FHpfqt5w=Cn&kJj7f$N3_; zNN~XuJm>br3pwmSJQ1F!i!IjYG^)=mH1Qsr#%Ib4Fjj!cZNB5V_bSpXxaIB%Ll3xb zz<=)-aG&Y(v5#MzVF&xttj^SzM!`29@h18kQ7$bHZj~by>{Y`o!A^Qc7zUg)6peI* zve8j+QPV1^40Lf{7AtygQgqaqr1ux#a*Z1Rw9=3DBZAC0nuqmQRA_vD!#;iyD&*B; z{t1gEBWPgIt7TiM{<^#FJKu2>fa9v`?+zafa^3N|)STTFsGz4Y%j|lipWXi2R$g6d zTOuMU@rzX**7PAMjdUB}<%wHKCrgC}nUBy0(xNnFviu>c^Y;vc4)1YxcLozY zDGkPh5(yCpfl!OlTF61O38frilh4KX-%!>lg#kN>0bL|gcu;TsitJ^Gp9D2u4ha1& zD5V1w^Ehr81S5>W;FgH$%$+=ryun3@@}0IKqn8EsZ_x`#>?PEfxQapisGz`%TsR0g zEXN(7P+BONHbA(0mN+`}dkpHKgCTU`aNsR^L-`_u-e3-J<%Mn6s|oo$BC%*qX(DaVck#=3zc5K@n+jhrE#dgxMZQHhO+qP}nosOMO z=d0^}zvpL-QRmpTRp;Jo&3P=ewKw1&{@CB86?$weEZUrylz}u&3NmN799`gzH^*#h za`GPPF9!$5`#aA_L$ZX;1ZQ!qco*4vohCVg6IQ4DKme#F0rJ&)c+QwA{$Ln;i=*|`@#k+~P=y+$Edt27jN$8#cCU!q?)@=$$7#67_(=saUNW`EOT1u735Mifsw zP%;RNU@*hj%Oj!dwXil(t3}C$BQu7>Q${NNlwh_YHUSGO zRt!qaD>@TdUM0l{i!zH=m0;IcP?jkVpEY*raIni_JkhF5>!^4NI^_L)75a1X@*V{= z_D#eK>{(KTV~~?IT$Vssb&;C-M5HHY$nWGPgg6q-kTs#(6GMDN;Aw((Y?RP24KUyrgV?)6 zw+fsI+$m_DsB2zChXfe;`M6>5!_L|K^Pxs9paJv3FB4Xci4bH(c z!~a7KsRuSswnsZbLKaMLi5v<(fh9{C*nJ7|!2`5qO{6AgNyo@5(Q=85lF={)v5(=jN;BeiLA~4M@ z6ifiTl6b$~m_G75gP$ogTfHs|dWXso8@hp_!3&7qY`JoGd8S*kxSf~-)ll7Tf0oc( z5}s|LRg!O(f!h1=t$>|TZfD8`d*Tzs@M108O)2B%4Xqt^J z+?S$ir~mnv`$cWY$Jv_%unvrULbx`TjH8yw>Jy?Jl>|whiqImuuGb=D87a^?Mu{I{ z8D>|!D3d_=$83^$)>KzFsOsBkLzp*waT?NEWLe5Uq(8C<10Yz#3-MsBFXMuwG&!Y& zSc3XXm5yaCUs@7=DrWpzI3lUm_YV=%vwA?sM%9P0l3+ktByVosTn65T2oa`{u(7&X z6-{CbtguAGG){YnW~Ts@!dN3`nky5yUv~M6#85>64NV3ZF-4t~rCLXwM4`Bb0ns?- zjnWdbT~SANb<^ycodq>8PJPRmX%Pe^6#^IIPlJ-ZBsGmZfzhF{y4;j7NwbNY*On&{ zv%1GCnrd2zJkdokl%iP}kY49S)M3$H+C%*IaE?hlvsh@VgNG?xx_d~Fc2LiB0-*eYFeZQ zj*($K1>i8`olQ&D*OCHsHa9aDEi{*F6tOyyj9W&jDxa44!Ru)fafo|12@>7|2v{tk z^eOP;OqPXDF2u#eT7e!CyAQs%INzl3yIHApTdM;L-nf8(3^gV3!9S1OxhCl3cqDZzx>9bq za+Khm*b~c37{OZy5aqixxHSX)QCNw_NoYzwvx4@_32CXgO2wEQsjQL){R8L+*ijWp ziY=TCuSFKT6KCX3Ws0M3xYW zAh@w1(pF<2IsrwIw6x7d4pDe)IJs3QEL!)-Jbbg2AWkFrQ88j(Oh$i!4II3*;KXot zi^7Rd7LinisOn3+22zWM>SL8oLM;jAteRo9bhMd?;xFVPIyAE+KUHX^PEOG*io|D6 zPc;g)7m+PBkF0>o#_ktSFYek&t%}Xll$M?zMNS&tO9nHLpt*0&Oa}~Jv`p;ZI3yBy zly)`}MWkH11}H1*l22H(&qPjebmEIG2F&cnwn{{b6*O<=v~oP32%alujV3S_{IaBV zf`JO2WTqnMWdI+@lc9InU{Ji~lMYV+@og4ssvLB~9T3d#U}`+pEzgele=d~nC*XZo zK3{P60(in$J2yEMITc>~?>?^xH)(-%y+hCTqD?=xSS*Q5=rpoVq&ty<*NvSn6EL|y zT2u*(L*RQH%Vjp7_w}DL@ZbCS0uA{Id2d9bC$sRafjEoJM#FxajR@<@?}?Il z{h1Cc_f)0vAl`?8JFBIGYZu-^x_gvW=nwJ5k?X>#7||L+oUQORHsz-qr_QnXAIM>o zS>Y1MauUneDgOg1L5thSvgQNC$=17;8oIK?nDo(ku;}W29eQ8{j;bYe@=@x|no20C z*u{zy8R{bsQ?M@`{f(C4r-_Ul%w*K?U{QWex-zk6AR1HRY7^u3A-|(A8Oj-w*d`+} zMDDh7f_`k!J!M1;h`doat6W$Dv|@*2>`a#K*H`2u&DhRWX|#052{r(!6mM@L0RlNAaX8XDTFkVP6XplXV@Q=r`_T(`J|Hw)bN{t_fo zNIId9dI~eAY28-Dr&nOAk84v&t9&PiOxYoP^_~HYtF(?$VPo+H z!_n$W&nBDX)3UISi0Ge;${g=@MohZl9skpk`Ri+UI2ekG4)1h2FE20S?;@Vur3|z9 zyxjryRyqt=aWqIp7OI@p#taQ^f3~pGdk2DsT8e+3Jv;(qTF0Z1@K`_*QNuBt>^eEP z?r3i&xe73x1*6&8y=Jcq6h}8{=zE6N{>&tE*T}A|Twwt{&eWrySH@!`nXeQhFe{(kmNWuKnY`*g{(Z1g;AP7kDLV$-as?S;AWu9WQ}Bc zr(!^y)R4+PNsO&5U=6cb`j+loE$9`TB z_~VuW9hkm}Q8&U)maTJ{wSWF%*u{k#5zOVs0SL=5A}3Z%_Ei1_pX!isW=t9?EC_*_ zqzpkKa^DbWKq`oK+>$XU_FE#4j(}!&Bp_rk%#F>#gpGr?z-1Mum^iRmc~e3P(^E;! z1i((}9@i%$8=aMcC#Z2|lyN4WSEQb&t4C}VA{s2hB~7i7h;mPk-6ESjS>!ZghF_X1 zp$rH$B^6OqnnZ%Dr+In+Peh05P=b{~3--l$Q1X#Ewin$x@uMjLSxc&H5l_|YmUM}i z*vfKYk;4LM>x4KW{R&yHfKbE&41X%6m1TGa2H6E_h|v(luGv!v@8%$>I5$gTM4ESx z1e*&|Qnzqe!n2Zq7^16EC|RP=(2!QP@`MT6sJAqTahbhCc{ z=BHj!v2t`GH)$45nf?xGrlqP^Bl^Byc9@L80b|?7YKlouoS*B*cNWsB=wUp=m+R7H zzl`R;THQ{k_lMIHqn}nUK=J_4pyTqbVr)L!5#kA+4@@eirlwwt*9A-73!_0M%PuD> zr6nf*+p@Ozc|TnTMy73=F{L>>e`j?8(zv-KF$Lqn=yll1l(?U3yxCvAU| zkC}C(kJYL+I^Dg4;d9!Elx`sU)3l<$r|?BpvWOc8;MO#C|4d$?VdDi^1C;-i&t>FQ z5kNQ&TWb>x4-^^@a;UMw$N)%^zWO+^Hs3Vu-04~9pnwFIRk)Z}ufnD8fE-thvbI`$ zly-YEPdZltXrI?b^=w;`5t>n)`r9EaTep;kbn|zNR@hsM|FrLR&y*(1Gyiv{Ec%SjrSnIveV!p}?F#}BHeO7q!W zo+fD=C@a!7v_#4t@u1gKx3a{tVx(-^^6%+>B_(_^Wns{FD^SEEY%PC1_;BU{usF7tSB zmL50%NV@H#DmB}~(s#1mZpr3P3h3PJ-nm5t>nm>8%*L{}$G6w87&oEucf0v|u1By1 zivH~vg&8Y>bNuZda^KR&d$mWENVWK{lanrqru0=2W-G|@qC3a(HB5%-cwn% zf3?}XB9ITOQ@P?sf=Y<`gYLavEP~rKuupnmRlae;=5?n0;6>a?H4*)v zcI0e~b8jO=q>qZAfFdo(tU^hK#y33c+y+B2JVu#cz?GI{g345j{!ZD*a{g+Rq5v&A zLWm(#cgiSByM!lpH&#~Tg2Wc262@%Igc3nO_Fe~KhHAbQLxD@Pi3{O6ThNvMd!~o=O_%L$&CVp@aM|PCab#2tUWIh@Ot&v5dwb zXUhkr*o>PYnpP~Hs#$aNlo?SFwy||2fqaTwi4G*Fp!h>{^k(8c+Ih-1@LHm7_9@je zUoblCIA=-Y(jJ5xbWCY~H7@*#9H|qhPvHz}Zbotgj%HuA7Br!_ra2E_(2krAT-L5X zDAh5WQLk}pHvt&-Jmi9ZL#evRc6O7wNLFu<8 zP7usRUy0(0J`gj?yy&KysG`N+hz;-r@l|!AKgj_yTH+fvBg?dW*$^oJ8|CCt z)MXl*-?%in^4av^f85|dH%*$Bk5W#`?5ZlumPNKRg<3|m$Qcb6#uR|OkeQ@~IknzM^H!YH?HxJQGi$i`((iQ7)=s0)Ve+9m$yTo^c&hSy zfG=NJomC-A;nT!t9Q&O!6bKrqqp>P87PifAvC67*GdVUld$VJ;oHi%0Y0lYv^w>p=Xk_)qG*3>dP`P2qW$5H^kc|I(-b7Ynf z@}s?g|78LQ!Ail_I$9a}jH$|e(9n2spRHJ9(b`uV7C5vYJdYSyGP5>+qR%7lI<0Ga z89lMVvpOT&<(C=9@{$!s-=Qg^gXUMzpSJC!exO6%`q(Oj4(@IaSFYC&Awz z>n~6XnlS@-peUP&?_+C!YU2B?#Km>gBK>s~%F}iiYn!$K}m#BMgu}1aAes=xeb!%55fqk-bZQNY_2x~Lwp*) zIzh|u5MUIA(UMSzSKvi@Yt^guY;y%4uiWQ)fl2{e5mJ}4zXt4|XT6_x0I5{fYwOesvLL7i$ zUK|%L-^KlF_cgol-^__`;@Sas`FMTdg6AXR4#xf3TQ;!%8y5=F593{fn9)s-c~ z;03f(xqrO%U%!9T$0ln0?uSf!(F#xHyyubc8{~6q{tFo+Hiw;~r^bmsSB`jpZ~ng@ zy0zYIr}+%NO=qJ2wTT?BIrhv}4yMnra2^bmeV!lmejBDhADUWbS*aR@7kGJzZ}yKq z81xXmdt%8hF;Kmik1s464hz^z;0WA#XOx_`udoyO2{8Zbb;3vOV#xh6b7d)!`5|J0$ShWT&Q5M}clL5jdI zEl}`m^88mG^G_KYum4iM@hEcU1X>oXPKh1)U@hf<>|jG@mI({|5xc_5#V&!4)-h9U z0Kxv>Jb#k3w?AGEJMIE};WKK0GynhhA!6}T@9N|4NlxHOeZn&4cK%57EV7o6J#c9V zmH6*qzDZ5Kp%}|N@HEcvfW0>+BuDQ9cs9ZXULyG&S;dq0a&~#V%o_xK6_^OmF|S9= z`u4$Z9sAVty&ql5n!Ehdu5*+N{10XePO-sWfL&35L=3~5U(0X!Z|#|<;!t0t4u))o z0RHjb@@5b7fCmXfMCE>LS?tr@J`M1ILBRv)Gy~xOw{X4`{Tx_LDLM_($GkNi>6A*A!QfAtZ}AX&Yh`?Mdp z#({X*)X$BrFbq2Pw*n~~4$R?y3$s^&7rp*W5cltXdhVkvJ>8S6WpeJxC!nwytN;=o z_?;(MDzo0pAG_xHI(zeHkHX8FX?g}U|Lq{T8!3ZCJX7bkec?4Gu8l6U^A8_R4?b|NlnYx9IYkp$ihULkRMtBtd6B%;;x03zJrV>A2 zo2$$R!E}MUxkBg%DQ;LGRcEmdii0_PA3XnqAJih8^1gZM&d~Qb-xO9O+;WXjKIm1w zqH{{T84-PRNst?5ZhV#1e`6vqL)_hTIwAJ!!?If<-z~E%bnkU*V$QDD7|S9(VfN&Z z|Hq;C_ip*yUQLC&S$*IBX0us;`Gcu;dGFGv-`;aIz$w?L%W7(~zguS{&nXwhH7)m) zd0&A)^`A5%pvu}M5cEj|(|I0x2Z4S+Xc?LHE1-=1e?@xam4NG}O;psn( zMoV<0hC}D!)&MB>v6z8?c?9XQLiivAdn`{Kgf$*j&j)&Ywo{ohJ)N;)h;^#j6bs%z zIB&Tw`3IAi>))A4I>k1Rvai}VY!cwTi@R7yAHC`MiJy6F1h22#yzag>g2z@$-^*~& zYq|Z{{@45VG3b7Z{I&jcK6sHs5kv&t4(UFV+NUcYWl`92yhY~E7wzn{+Y&6WMW2~Un2LH$~u z-YqZ7!(<1zVfrD4N7;mAg`LV30+ywCLw*=T|H zcobkKDg@pX2>l>@&cy%0EfKCo`#?&E1)(^{p^@7<(D#=~Ycl{hJ`-Vv)!?!ViIw@Z z6|39tOpaL9`6IIEl}nkYbRe8Aif4D*pBmaIagN|k(Q4=)1&`o6s!X9d$1>cLWeKvs zM6S59Kut{OTWdevakwyZyJ1*!0y;VsU+T;vSynrBwyAsPkIQ1GFI5#g>w`aOeg$;9 zG=IVAA8jrLpno^BXXR5n#ryfEE@#fbCHUpu(qkcyH;yYj~eVQWb%@i8r5AW zh|$?;9#1bpK>n60Z1Rdg!CXWfVGo-!;F9yU_%2%BcIwPc zwK6QWX~Z4wEZ;`RPJa=2t2cN<<~Pj0Uu!6paTxX*qPf4;TCS>&F*%U-xw`n(c zTO`ZP(cpf)ID^}DXfOOihZWd0Z@d#LUX~E^3|zk08t7BH^ti`j$j|*6wR|t1%Rt43 zxQl?=4e3|L@0uS~TF4yYo)_dqnRhRO za7vZW@#;w`$0_l?KHIC-rS!qo1ilgP4XgL1923p;O-wC*?%KD9ii;(a+rt0;0bAF( z3VBu_v!=$S;=E_t>4X32O~A9VE+OZcKe_2D>I-2v)nf<4zx!8~mvLnE`>As0UqCjf zb>ejSq-&{$`x9l?I`gj#`r3{pd-ZSP@*SqSBVBz2g5%_ya*O$nz3Oh(r>Zp2WrYLs z3;)H@_n$P0Pmmub3m}5tPsq{c9>ENHQFQEA&Q!$d$9!mFN)hxZ_347e=7`DI5W%7q z)(15wklT{;jIGGYKj}cH5B+#B(#I7Mw8^GNrwP91lzK~qJ6VpGczqKD^3FA{=X50( z_?#Ee)e(aqimX?=*K0QR9m)4SIk~XBE5RS;v#@HxMfrLj4`YH3Qw|(J%Crj9mKqco zv~j1XoAK&}K55Ky_RW z)uYz}Bt^U$GKoe<|H$&hI7gW`DcqwPJnI_JD?8<6>Rk1lbLA|%*65x~lkmEw={ddf z&olh@&n#P^`}xgZ=ldUD;%Agj|GxJ>jc3 zk8(j#Zbb(ezjByVh78c6I`8CDwS!rOteHHmH<7LgJbREZ0DVBIzY^g`! zBuR24tSV|o77ZY*n>FMBVnlp!;%^_uYUG5E@=>R{0c=UzTdeF|{}($#Xd@mTHVzbH ziyQ{4zHf=luRK@LsOGD>xPeQPq~sCg+lyU6>*X;io*U`XU&(!h zskUK>@HGV<@xDk><-)8O!#!LpJbJm%!WpU#6!M6UDhD3hBF4Fiu)93E$Xm0HKM-)r zcj*%T+C2}F{bg(Vac0mKjPVmMOsfDnA*XS=1dZqyNT_~(e8~~aj1&3d8zC7!W=c`~ zC<4C_8hxHbX(krefvl0?A#x(UA-gvE z=vNNDvOYa7=m%~MGi1Tf&7o=pSVQ7P)bwbG!CT|w_c}`?2Nb-sN7Afy>Wky7^dHizh4)%8S56wn@R+PktLMP~oYV?-M7((7 z^x8$!GC=6Y{%v`|NPT7nvPFBSz%;puIA;QR>Lc->ThY(4QDmLmTszfL(EF1(Cz>>~>_7hLz?yY=AUBgB*e9ecc;U9uVz2 z`33jAjFxc=I_ZD)Rd=!y$9o#i{&)KYiZz#EnpA%}b2MlA-*UVYNJ^zRl*NzUZ~>X| zIg`&;nN{ocguXfEjCFMHrUPuf0?An>~~7CHH1;_pa#FSlq1co+ht1XC*2cjX+I< zUPig&(A(k--5B zLjiq3+<8V>@-*-x2h2LV{J=f1IMKs%HLF^aF7N_-4r|XAKLAl z92l==+HnEtJ!#nJdGA8vFVrsMK`OaiB@nZGK0F&br%~M;)W9ceRvU#kD!*^<4%S(O z_pg5xGHEe*998@^vH3hIObg@dyms8nUyG{2I^gzSTL1ZJDDkhKi9|HHHA*wpN zKx_m((SP945w&N!%bDx2%-U95L>ZFzUptQk(Z3B0`F(HZ2T|uD7fns^cqGZDsI)9) zeZ#==Ch047aPMW^b81t)UHyOL?D4=u_3dT%KW7nxvjRTh)bfh*Vx`N20t65%q_`gE zyOa%|yw+MC_(lWx@K*88b;~Vf5T_65^)VpgxMlY&rR=~8f=%myrw)3_RhVO>=j-IT zag)?_*Er{vt`V%5%WebZ#mLww8PVdypHU)eX;_!x#K7BHGx32WmHgk+d4D_I?UDt6 z>(!rj_wa2j2JMqdx>0;?JiP%CcrTUy9OAijeE{xWGh7VhY4j{Zpy2Na27)$yO<6d{ zdr>!mcC2eKTdrf>C+XX*JiUd=0obqGd2fuZ5DRHE)4)5*_)SuaoWe9=##1O}1P(<82B2EC+rw2yTpUt& zr`c}z<9e=sZB;9Ecqmc%6LiIB15o)dy_Q=POiYTk>MBt@x@wZ4N}!3^2)4SejID_J zGGlO>nS)*4iFDGeIcV-3%r8}55Yh~Dh&|dkuZ`dw%NH@dY)3+fV7tWj)?vC+{$UMj z`sJ*Aek&Qnf7JtYkD}DriI^INrxsV=D&*$s>cN9wKe7synx7an{G znVBkDsz9^CHCs@=dZ;5-wA{c*k|}SURY?st$)H*#IXHm1xB?R+!kESw?g$ye%fC}H zGXMxHj0ThCwCEs? zhEo|DLAO*wbzX>Fs~<=cOm%TrcPG4zJ5~u zxobY}#u@KH3Ki<%BUlBz=8O`v*F}mW9kUKXBhrctdnL+VMF-;f47jB+Iu+R|+l`f? zb}4Zrf8m{k;M_|jv%Fjxjt>Ej-x&hMUmbA{r|H2Jq3A^;KP)V?1c>4_)JgXjED-vo z9?7P1680qVC^#C!j4D;Jh0r22+&>o5WE#Wbf}8gXU>)M`g{1w zM=zeeM(EqS)5AHx95DbC#y{pdi+zaV#Cx1y9>Grca7w31W}J#NwccNT=k(ChU(DRI zo4{|*RopK1b@nIk@$;OQhw%~zj}~Z$n2nKkRpMp@gZwGqkRV*c8=yKtu(kc8hPjG? znThtiZLm}xc#RIM3<4L86Q7(=`!Yl|Gsm#WaAYGucWRL%QB8X$U`lWF$O6g}lmRJb zlF<~wgu)7#RXIryXx$nN;Kej=L^s)TO_97q1G7G8yOTf?GcPI+fL**$Xp%EGSmBp0Pu;`W;gy*Zr_F`-9^8VRcGHeQW`mu2^NWx2 z#1gluaYTf8i=dr^h;4xg*57q5=qK1_TwB2}Xa#cCEU@R0QkuJ)Y3P=7%l7VY%+MVXaCcKDS3t@{&g^W=oA|k@v z%JY@W*VU!R@HP}YP%i!Fh?A!bEwuwq7wF1Do{~&T^8h9f7}jN znJ=BJ&p95MIajKx`{t~(SFb{rEW?vpiVDzTTBz;NrK!=UrUMi22}oh~hQm0g#`-eE z55y6x{{8tn{IIBGsM@a(iqj*_GUYOE=RldbKe8=sh4z)XA<-!XSkMytoV+@n?Pt6} zR=zMIrZsE`@Y~f3vFN*bi?irqLK6ntPc~STsWUzLnptp3;J<%Fh}Q|_EAzs~cH<~w z1dlwal*>apTmOKVP%MFfIQ|bohXe(S_(fF#r%d2(bS0k_U;ZI+{P6zQi%+s^8Zt)-bY|d3IPqra!hnceu@^KyS ztiUlUMeqfo9wDZ9>danj7lXcZxk}jRBysFLc=^eC`qDEMfSJ zses(>1SJ&#y?Y1l>qN|Gb^T>#F#@4q`9i$Q@|EBb((a#&-0ELG&lmNPs#6CZ)Y7QE zp#3SFwKaLquoYrL=Xtt8aeI^E*MjHHlA4WiF%(^m1f#z#fEor>jtyJ{aU;Q;v|p5B z5>W64NLA99j2JJO8}AG4Fg~7>KVn+)xe<`lQZP^Hoxw=J>Ac{cc*q&gSrf7s7}GV% zs2#Pu49W&)cG?_`0RR9shBWXkk|JamIck*G#(6d`{_s}9^z6<&2kq0@5#Zb1*!g_0dc@C61}H zb!s65-H;c9NBLV3-O??e#JVz9f*IOSji`$8aE3b+Gmnc16P|PFh-cjATRsfI?e}`K z+c1(s^yFwD?UvCp9!H2@3UOq%GaY(O@5XE`zUSzBOE|@TM__j2db6;|Ml~)@WGa*^ z$Y>;jOOhGGpw(n@_T-Ew89!sf3Zm}eayAFo6Z%jt0sKhxph;SeQ$eGm2A-Gn=96TN zwK$rV#vpyqo$8r{ywOfztC>gbkD~1MZkdW!OaC$H%P${ z=VqepgqW13f}0rCie=;!79}E4WIZEERc?yR3GBm-7nfgQ3o=!?XU<|EFk2|$f8Vz3w^n8V5 zr8<%bfbuLV8KD36%!XCA9$-5myG%JiJe;E>#koA|NTRh^ zkzZ0oW(A#yhaF=D`lt+Rz_fS%dJM6Eqi&{+lvzgh2kL|fGc}oNdweBTcwNhb6uU)H z;v1ay-?9~gy^Sw*^6uZ7W zIa^Vj5djvl6Zay0sv>;AaZ%1N<;$37R}OWj0eO3Kn%=6Pm&!|MCR5JuoLpI=6ZFQ; zQ|`M}Nuu{-XLqzVGHiK{sD_RLmg2Hwovfycct z7;)|{s_E%V9lwYW^Mc5rinrEE#?&K=bPiO1E#>PU1!dB7HmO$-9 zbXAv5uCh;s^L1|_6Y+C9srJ%;dh9K=#8A_P)dg=vmMcpAvmvD|R3XV{1%bh17m2Zw z(AuqFMD1O*NW>93wE4+sFS*?(BJkj`-EhpkqaF6=F(M(`yon&5h-E}5CX2IqLr6`b zRJn``2CYlMKwUl2Yi%Kq#hEN5Mu}bP3E|3*%;EUZ_ttK+>2$~WeAFB5u+S8)d_iwm z#Brr5!4X6OMXr15_geFUvsj49vgN*0S7L=K z^aG{x;sNoPAyaJk<0cTuc=+WziyidOV2%ZviwT8LOm-$_(~z7|jw4zB4TFLtRhn{{ z*TJ}dAN>wmF)?eoJOE(`N~C~zIWfWj9aJnU;`v|>Cx*JH0$*!uH^MJdMwE1~kUEO^ zGoV-`uuv%D4=XWL^U_EVc1-lgaXu(2s)C+EWy&aGz_Ki*vm@o~C@ef>h%(3|X~}_z zrS6<`dLi{neQKwAL3HhiCEj=oEAML0ojG2JYS}nw+SB-0#5QY%Y7jZy61`CZoay@g99Bxoc{paD&k4I)Z|lsI0=M zAe&Qi(X&#p-wRE_QiKP?M))3|d=Z)itt1X;HQ^8>g8A52&A=K$GUvYtkUWYwtFM;&j?@* z5na$$bSTWs_zj4zT8ZpF+NqW8RQ&J>NGPj7x3hrzjV{RYf<{t|tSp92beA2@ts!W! zGYHgk`S*)`F8}w}t^Y4|F)CcLDtz(8Fq4bld%7AbDr}BRCNAL#5NGzYDug7gw&19D z;K+Z$KEAtub>k8tW2=39`2k8;*uW%J$gynt^96ZlHy7tvDs8dC`Bdk`r6#^KeTva|y54SQB8sO< zp6u^wak)PlRXg>oNZrS02mac{B0p;CI9!iwI1$`HXJ@^ZpAPREmgD{s{UJJPJrpVE>qsM z4A67vuwy)OoF{82C9$UOgGSfiYkGde=^G_MFJP}@?t}7K+X#>$-B}a5pyE8mWw7Nc z?QY44zvpuKfZUp9!{M;}@9V*$B2r}Vl^6I}5B@frO&}ko*JWhEseYaAAqv(9x7~h` z9R=fRW&H5_>!Tfb5b6Hrb8l&FRpUr81d|7;OmhpXC=$xo$78NqvsH3LzbbU9glnRl zBR!C)xNa1frgkc>V+DZ*u<}^1)f|tn2=s&*TC zH&6&jA&MQ778wFoMp@-H{0sC1QjEfbWlM25y5T_nN$!aW8T6|=23)tnt&}3Iv)+Lo zm~};N%$yJ7G}eTT$%dw*Yh&3xdiwAmvWp(ykp}Lk(j$-spzvOusX{3S7-zjpnP<1(k;7`2fundp?hH7g0bvI~$e^Cl^;d zkpM3NQa^I#WwTtIdl-Jh^SHQ8-?RKDJIJ7sY`Kac5Wx`wJDtu{kC@6$h=flH!&mFo zrAa^M34J#Lg{it}jFV;P-IE8E0lH%#sO!7$1EubZu&}@o>ku{fTSE4E0Eq@wpL9H1 zXDlw;0MCjy@daBP#>yRmR(eoEhLqx{GEQ`|L@eH$&5#yeR({1oGf81YAUC4XMLNwV z#&x7i4siMMA+qAE)n?BH;LYV=OX-cmwW!($FPKFsEdrNBj;r`#Rz+)nkGDgPLrff) zfK5h@A<$qtyEJ!D5vrlPW>;1%ftY&9>@l22?&8K5Db^EEP(cA=pc^k9rJDNo7YCXY zjVCkGQMZYzu8n|?!+MLL!}4q$$99t*oe= zqLDf?=KYIgZ8Ngv@|l+YNN!zL>ByBX)~NhIh8#_>kQ-&lr#Z{=4YFUJeY${T!lgka z1wo~{w)$lPBurHtODT{Pj%X3z)*jO%p7bN|7`NyQ-6tyy4m6(XbA)aFW9DFW-5*fC z_Sd2a-U~qPxsDn`&*CbM`d1%Etge`j*UX|g9fsHZ-B*~AYR{dji!_j!s>G|S@rTI2 zq%?~ex;K6zrM9L98C)=4P@@&-`JZpi`7t%IM2GUJ#e2*qV8oPP>$Wzk6t9puJ! zDCP3PSV%}E!aN|Cl3Ah!d|0EYnLVBOguY2)&vzZZLWNbp%k~xZxGa~*Y0wTU`l+Jv z9p_gBNf!+8Jp%p{9lGQ*Pa>K8UtlgYv=$2{4n z-vS-sqQc3&8NVKmVz>Q4|DKc(2V8VFb7sd#?f03I(4?_&S#pkIh7t~AhlMDOlH@=7 zw|U?d8fec!3F)bGC$Wj4(B?2#9K!U{uSPAiw~NMg_l`8;{6;&IJk=?RBs*10EefKg zJ<+RFH3f)ENJ2B@k0aNBaPu_?fKW$~3)_n8TUqj{D=U*e_^Hh^voEZy9O9!1%NVc{ zK83r)7!AM8gD{b=R4`uXgO=3CkRO6^(D%}%*1)7)@^*2VHxt7<79~v#$*`>wAu~CG zg?-?YC$6Z|`(o~KIKRY%jg37Xg=MmcpiZILx+x@iEirw_>HUctqm_|{y%$qyY+x!; znSfcUuPV#V&YH3oqO|5Q|G0LT$o~z&m@Mr~Dq&KhobjRn=f%tG%{@t5yp5O*b}y#D ztSIfQ5n0(%_C|l@MMi0KFGLN~lrxnm%X$1LMY(8Nr1+cq5-`rsYNq)dC5SHYfS?+j z6ktWpBmdLu$zr%6QTRu>jvkmBzl3v!de%9Jh9ORy#(*qz5>ABGE~pYz#>Z2BUI?DP z>z`E+Ly8!V$5RY1g3vSzA9*uX3mK&aWNH)?f*HyF`6N$FyEcqKEkAizb5W8|hg`JV z<@>+#gaM@4xDD%%Grxo|T=cfvOz{U=tFiT(Ee?;qKY#zybK3;MfVkt4^2e0TEqP^M zG;PIsbgu#8(*>`}kxoC{^kfx*dz&X;Zgu=xTHlhf%i!ZTz$>~g z2F(X=m=6+vV-qD{2H;(+?Dv=T3obH11@xSv^V2ZYN>N+Flo|ZC1d$LZb2Kmh>fG!yG1{%b)GG!r(p zSOh)QRL|Z7Lj{O8!%nfQ`|G-z$0GurYn&uq9Uvt2V+&&Siet(mZ1eJ zU&?f{S6Y$sz=)5u^te++1OIbK!vyOPNyMm{gE_HybKQ_Yde@g#RW%j{ReuDI5VMMM zmvIzh7ZxnuCA_EmO?e%IJ)6Ite4XYo&_a@Rz(hvVgya-acLY;&UeTG-+)f6lNyl;5wG&f;x5a1$< zeg|Oa#mKmlkdc`Na^Hb9muzjB1RuhI0Y|kIHGP*wanW!@bn(Q(F-#y!1&AR8)z9a! zUc0VTAu|O{lCl97C-_sg4s^;`ODOc-kKtQS`Dz7^Y%K%9Jr9Y-_VIWeR#z=Nz?!&W z>jd_8IuBFRz)~dM?l=8+L-63@N5DD(*i1dtx~h;f?$1}Nd+_g7RaI+eXFvnx$8PcG zcq~5G*@KQ`9QAIC+3bJEycC;I>A7B?f51vqk{D{C!-d6EadleFXA6PJh=_>rSo+#Z zNI8t2Z+C}3e|GoP)!D7*F*M}azby?(kt^fDQb$3>2QQ?`x`8S}`7E!lK3^332cEUN z=UiW3|2@x!T8zrn{Q4+NBOo9kAgxkT(%sTIbVy6L^pHacBi$g~-5}jv(%s$N&3y0w z;^UT!S!>pubAGY+et=I>-@yk`x%T8!BrUAU)k`#(+})|C_xh|)$+@#+KUPb9wqDb% z0jeBuJs%*jCaN+2)xGh#`1fMVOIkFgR965{9WB&aKQUCaOez^b0N|jy#%xEgpy#Ul z(@8zEL5s*6jA4CkY%!?Hh#Lr`bE7@#Wd3$C*4R7Fh_=Q0AUoNr-5iV5R+- zaik#EkLkjZ6z(+$Y_0QMH(cizq|Xxlpfs&!v)&*~5*kplkk9kI_SDY?Im$fY=R}Ix z$mF+ouuWRw85acIImc1PyeUf{IFtp|mFz66SLxL)uHp|Fywj}~Z=}#FWsKV$h0ja) z4Ujc78)Zbf-swO|Y}nM9X|vpLp+vwmN$s^%uGgF{bbk-9jw>2Btl}i80#EuCk7Z#+ z2JgIuEvKcts1db&nKZK%msDg|P8<=$_VAqgzC+eQZSBTf!op@O@3$Ouv8h1@yQF?kHJ+8$FSMq@gC~VvXsAO*4H}G7YiRGzP z7!2C#cw-R`rqJsev#r~s>l+qVTUrslPolIE{klG>k>TQLjGu4diDWAlT>ydeM!+5x z$i}E&2CFLIH~FRVH~<0qn`v&V?&rd<{d-pX7BE4aiIcDJw71$iZyJnrfZ?@wWo zQ1T`KDg?y}27XWG!+mpe6$S=NN>~E@dvrmU*rYt?i`EsbjT_;>&hJ=1^q+J3ue4aFou|F_JB zIj^9>sE4wpqN~elKANhW1NF!?l)95CoE%UVnU+>FVHr}Q2%#A?ZTYebG-VB|ftkL3 zJv|5>*2n(4?-u!t=F!$>!6Bf|+t~H7FN56k?X7?83UQcc(PFJ}e}sZ(3=~V@e()rb z#*^s@9;uiKjR;gRwfVkUeCgBJpvLf#~~=(a@g#RK~r zcB5tTVnUHCIZ`Vsnx>e=H<(ifmXxMPaJ3aZQd1Uf+*Hm zJYn}IUG7&y0wK8Q@K?}4AbqYHEL&Du`n*_X(AmMEj8uM^NIUxt*=!^Y<=#n+5`9ch zkgmgXslEbw<2kmrtSy|2v-r03GMIK&O!Li;yPZUXRp;w>@4<7eYh8AcuCGAS*ch^= z0Ve53oKVE%Kr0R|E`64>VRrLb;fFn1KZ=C-@HHU9YbKQ0UvIsd02{7M+j0ByxS!C!RBz|FE)G#>15d9G20QGvQ?dFcPed1Qii(3fV4Zr}fF68W-^<$yy5~hN zVY~B{f`##PAlN*6VHq+tXNQ)@tHr_=&D>y^kT6Ql>u7WOK-jTqX*YL!#`i@YBkuhJ z?D{@u4`7PnYbvY(Ba_L!M5KzVS&r$Fr0J?0+TxNRuO|}7R_K?N0$@eCX2Iubib<##z%-#O>|v%#lHwFvQ1_igfJy zyyf^R(D2VDt5xw%LqxhNP$T^ZhJa^7;6|Evdn$8-t66Hi8u*okC-c`F*4*45NesII zW^hGPulJ+n0jdS57}BOAk8=fM$v%VlSHAHAk4t+k>4t1+L9F1%!9+jp=iT=97VA0w zVT~5)`{BNDhHxp*Rq$4LihUdJW{Dm^XG<7-WN6u6{%qlkz}$RXEl!VoL&5j=)DM;1 zxAAg&3e+tD=d}|bpOu}>Sy7JQd-K>-pJ}(I`y9Sg!IW4^Y^bjw6)74BeQSMxIa1H8 zQ?KC{qp#Vk|yjq(m>#^LwBDP z?7TmuX)@>%Cryt@BI}*}^V!SE+Gl6%WwU{ELqyE&Qp-nWLzr`S#4iZFtm>g~#EN%J)rP9zKU&lyvOER4i`NFrgee z=qS_aA3i~QK@HuvdiP1s?w`78D}yAYeJi1EQ{S5T*s91|jig_SV#^@U-8oYQAlR$h z87g_T>&YXXYJM0IC;G?Hj0{h#sC`Y?BSS}Ko!tu3v(x0SLBSO?5k!DY&cFfRFxA-& zg<_MSEF79RlQ9)Ly>G`R0VUNE`i)Py)3H%y$JuIOoM zYpUuaUhWlZCir>X=aJa2HhA|_LcFrK+a~)yb-(Y_At?G19tT`Ri>Id%fbej7&Aoyu zI?SpE_u%kwgT?>pu5_F^y@F_arB%uoepCRK?dEoh4F5D-zoxCG_Sf=eat1hIKVLY@ z^k`>GwGmrct!L-5Qp-r{!`f}THoBkwiyiHY#;jlS*rT9;n7rh3i#|#WUYYC#)gIAC zP~5~)ygXf1Fv3>OC|Yk4Qh<_~T+TIs)boj~J|Qs?_K>v4`Wzl%LQ{5_tWBKoJ(9xH zWk)WSW~A+Sk|YZXyF8u(VlH;ZgDzAH{#o$(#1a1U2D*^dmXk{c0yvvPMXIdS(7jRQ zpcdzwp@SOpf62EqE)^Btwj-CyIV7^*EZfJdtgOl_>>I9bnWtysi#!VQ%@xAsh|(g3 zE(wQYUQf^3A`!2bV-}NPs`|Psd1Pz#XDo04*T~IYhLuflL}{Wwy3182?rXc3C|{ay zr+-uLkKiUg@zv-|gYKzRp7=s-29l#NDFo5s-xXdDru$!ggUL`mHOh2dSAH#(AV1`L zo_e1!M;`N4PlY96@7dO!!;HPG6mx^S5eAFO@#>T zM!9`fnjf(X8<+=l{^UF!Z$BzWPWB>D%O?~4678<+XLs!SwJYwn^Sfyh(p<87mWUK- zX@J@pG|RKDG8@l?&b*VWL$8J1);Yca2k}?AOx~?>AR}_UWhO z*cgZXg~N4!&%&8wH0oxe4WiE7Q$ZLf(vE}UgD547y&n$axAyd1hZF5qTP$CIJ1r>z zG4WrzWbSd0ZN(fY&3(gQ1Ourg;j11HpEneUv6r!bsN3ezo3_?~I{O+!n4yWeB7SGK zH6cYI2yhY!bX{`uY-4{Sr`>(q4d@8=Dw~2zJKdbqkvPD2X)y5qcoz5Ca&5umKp`t8 z?b1>+pK)*WbR{MjVK^R!VavCVam znvg(70wnab?f*a+@L?@l-q!1-?1EBCI_7!}TNr)Epz$0Xe8#|BfgteD_|fzzjqHgS z8qv1j_3+W?t3hLVVXl=*AzoU-Txt7jzK-dCPe^&$(wcv#-J1}q6q!4%osCcVKaZ!2 zDUE>dIX3_r+0~%yqRnRffmVmlY(zlV!6b28IS88!;ZI#ptVWICV7lGvxUpW*48!b- z(v{kEqzWD;tdL?AMrH*(<-IkMmBCfjC@X2LB zJH?J*!_~yem|Sd5T-lO$24QP6c6_)aw}3T305Riu`=?+M5ufvyqHE-5vB8QqPJ#7) z#CLrB;gy=_4~y8`@F<7}*pQPm`S;BVw^xPJ)$#(}d0Sk0$KC zOyQx!=LRHsESO#iHnhDt=LZ+&o?!p1f-X-` z97lsx41e<$385p|h#ZmLUuQ3s-MqhVEucY1c_%{2~CD(Ucbz`H}lZ_^1COzw&s)$W=(oBBidXP5!O$q%aGo zQ2p}?wVap66c&Zh+j`LqID@0p({y3jw|53vkO)#<1eP~->uylKp<=mczSFF-vvZlVfRa__ix6&nU=RbS~VDfC3Yr^N5(lCsy*-Q z8rbZX8=Sc?5mBcIdoC|~ca&K7%`NnPQ_}InT;+jb&q_X@!*WoIW!S80j zSs$T&VImEd_7{JVyL!cX>&P0(f9;s#*AMV_%S%g<>fmPTdJSoLPTqd|U8d`ZzwUB= zySe$J5JiogM_)l*LP7mxwv6AmWLiyq;tSgv5CYX7L7oPWlA*|g$I7U(PyMd2nBmCK z63T*xo*cU2v>TR0x{+e(*11UQO#MyW{CP$<`K}u2YgeQ7`(Flr zOJXE8`@xGmd_SgzH^5|$y%S$%Yu^Q)UtjcZ%+~$cqwn*^T{%j zA--oAm*%oS_*Ye$3~$k3?6w3XpVNln8X;}W09hQ+5Ii(JZq=XI&OE--h91JN6WB)A z^z_A%Tm@XViyZcL_#CKFtd$P`(vB|fz0psD$gveYlTYQMkP2(4+<|k83ek66pw_!! zRHIz44>uHH!Bb2>-j_Ln*6X^CxZp>J;ASCMAvmRw@J=o^x1 z_UcLs7AWG!Yu;95Lo-g_r zcv+{J-^FTonkY&bS0=OyKmfekEEiY)@9*zJ3OxuS3%28PlRv1agF>rJ{`7Dlk!e7) zegh3GRtARQ9(XB#TPyZaGku&T7J$5v(4$!orGYjCjpq(96A*uFuxj~sxMw11U5?XM zE<67~xV5md@?T1BioNlNFLAj9CUO+Ql$N+0ETvjfpou9zJ-8GyWnm=noA+NW(mDW$ zIf71M;oENyB^r6YpQxtDEQvcDXVf(VTiC9Q{q0a!?*oAd&TPU;Z9`KuCWo_?J2RQO znlk+2>(fy)na@E*h}}qaHXmpLsymptZ5NQ<8eRP8fbRZ63x`I?2WHa;?67238t4Ks z{X!ImU(h-}9TNxJYyypR$6rJVctweJatkuAuFUSVm=1VI5c;}kRuPp@E_0v$aUmKew{Jc!YJ` zCMt^ccP-IouoIccsiTeK>4n!BKlu)J*MD*mTle{ca_$ZE_LUW)%Hz;%4DdM#3E9o}MWc8fOj#9~8*gwqu9HlYs*-*nKT-@q zLGvGxlAw0KG`f%I8HOipNg|1HjHG-+MA1Ip-t{zXFpcZ0J>Fm5c8@hOa|E0+?vR*S zZ%U|ZJ}n!|b#d4%RkKxA>-#*Iawc{80YSx5Vlzo_jQg{i?T<5$4wN!9Vnbb2VpqZ% z@tumZtIIuImGI>QLKJghq0@0lGz04gXlf6e10CMKoQ8#_$WK|D=sE|whR_2)2W4f* zICBSCe)uPuWtEVfJ89XztygOWl+Eb&Jy)l*dH{DzNH(pYsfo|?N744N_8ty<$#0da z{;}+dm+FFQN2)%rV7hlf6p%|$Nn+b~Av1!G&>=Qh1gAnuy`9g|Nqvx-r=d0%8Ltbl z+ea5bL-E?_ow=|Z!HeU-=W%phZiucZ_pt>q^a>;W1!Fw4v9fBKbHX>%TW4)g<$p#H z1gvlsGZkxgwCHiQ6B4Lln9+HM!{1>-m}&#Vx~1e=pV9H{7)` z!5iSepPzPYXlVk^S3YPnd0vfhBL?~0#NTw_l(*i>-m6DbX`T2I!oSN|o}at~$OVY~ zgOeHnu9rlkTJr+lF_0Nhn z)s-f%=sy#7Ah8Y3==k;NtUtg@JUNfOKdo$;wJV_cL573U0^5t<>*IG#!6e%6=AIbu z#m$8d7l;p!;7M8X$d9RjDtOmIjxM!MFBn)~WtY*#?&vd=v0YDc^aSXXX#_p-kAitvxOS_p5MwL{hK>~ zlQ0GEuY@mU5&BpOMjUmi_AmbQlu~F2yLQd1GnY5)1nHO%1tbLQ3ySdZ>!>Di*hsQW zZLXYrthYAn9l+T_e4VVD1@y>L8xN^5ABVRsRI%T@W$_2brtIebA|z|bBje@!eqvZ# zZ8lhSVEQt`|9kL0{$+x=UQ~9JHAR!60Iv$%TQk6e-R?Lim=tz+$M9>}qmciFlQ)B$&Dku-v$N_egTdKstQ)(~0^e~UqI#cF!+&=dU znlMI_n@r+A3G!JCwniiB=+ejp5q5G+|J}FuxguFl>R7gGI-v0lU~V}_U}P|SkNtZ2 z2?KG(nO1AimK?qadv|gS@+#*VMv!%Y_N;#vU6-&Ja(D(?e}XP9SwXoTfnW<0IW`vO zv1=#&?39rL#pBghel1e}ZyM!bPNg6VbgGWg(Nlnwq5t!BS)1J~deyOFE9S%t!EYHM zmckD4i!KmvSSb4RrsH%QCpQBuAA7yufe+7#9Du%e)tMZ)I$%Mhe5s)^Q?^hCS^i@w z?@Gq*C_s>x#bDmC1(oI0h-~rb+#IpD{a$Oc^Vd>!cO+#Gr}6Z3KS-k3h4cTjfDs*y zQXhr5$qrsmMVD}LhaZPMk0u;U`;sCtO#ketC2F?|>9)SRazZD~eojYKS5dl;OtK{j z_TP4g2rY*AY*Cv!wfe+pOp&+K#*hB`=0%T#g9M_nE!Jl98EPm8SGNp+oQ=g_rU8G8 z35Q_1Y)bZA%sV^Iw`4lHH8kb4-()i_*IqHowdN6pFX?Fy7Z?Zf5$%%l;-^aj^jP@Jm)n^F?ddo1G-2r5NTG9}=@S6`R5b>de&E{>fYHF*LaU)!KcO zR_S?1Y*=Q{bh>CcMGKF5v?+HOG%a67-i<$lNg+hKeI9SE>6^>v`5K;AE1FZ{a(612 zBgvg0>9sDrhmq!hsQNPiVPV>%Y_a9F?<2#n7Y|~y-@(ihsU~aXE#l;~U z-XtYTeY;M7WI0VHgNIgpW2uP1g_1A1Ex9Q9UkwfC8@+@A2{YR)aUz{II7bG|IOmI0 zig@JNqw0+Zkwl-`-#*R#Lc@D6`_Xh}db%qt-~`{5pg)J)n}A~kt@+8zQMm4H`$f1t zTy-*s<)p1a8`-PZVNn6xpHBJvhcU?M@fQ#;a4T_9UNTA87 zGG%ThJvu~*LmsApjvXD~iO=>ErBJi`toxzD?RnibubJK%_HiZ`23GOxIk@p=KS9OW z&}w?53;6i?3*=LeV=s)f$WIEIhKDHSxiC-yKEy2}vV(rPFQ?Ud5n-`MS3hS78K8ZF z?Jcd*R6h@>4$qeBd2aCTiNwMw`;F_U;}1|ZA#WzWM;7^dwPOB)<-|;i)qS)+1Ef6q z>5}3Kpcwr|g(asq2np zBnJ$1q+3*DM6nO+JPoL3y#4~i{zs~PaT8ZO&St0iX3p156PEW1b>^X>=NdY#}hOjH>#R1|8Ug)YMneBaZSbM=Sy3X zg~#^yG(xA%aeo}`kItCD6Ce__@|Cg;IBWD0&-KA7fTyKD|3Gs+1@9xi_lgID`Td;=ME$#P*jHd*gft;y8xMTr!QXD+u{N zvRKRiH1NbeY+ys)d>g=k_@LxQe}=r%7-?O5r1>5C2W^~%Cm3&>bxpD8b1<&GRrQy4 z0Oq9B7SV_=-bZS*(*_V~<9BudI!}w^M%O#R4^a{yrzowC(Nk{WjZ%ZKgg2=ZbtjjX z1-$0pXpJT?q}3+zLvK0E(9KefFi?}b{RNEjIw-SP;MApHa*INN1IBv3x0(8M$)b z$cX;yC)5s!?B_&dQ?{zK8kPqH}z?!Ba4FXsQ*_SP$`JHbZ zKkP$Y(|>9m98PEpiwqv*c6$B$%ea^)1z_hb59wOo1U{qmp>KRdL0o-b_DNt9$D!Fj zbll1FjvVFQ6KHMTGTeRJNo;Av`}6!t_T(4YyV=n%kRL*T)~%U)E}(|Z6;ZL~iXBHp zM;D9;MjxP6OhS{zJN$Yv#`7o>>T3EGoa$4ykN!(}kO`X)lNg z#C$t9QNXLC{enb;c1#G=+iTs;pNlHre^k);_8CDJT3<;X^nz~%ch_C~jo<6<5?;i1 z_1jyV0E}zP?AQL`D(~-kbf<%_p5hpZo_E?$gVGshn$t0^4j-vkQYrYWaGZDPZ#h1O*8J~wfqkCQ=IA zGQeY3Vnp{J^dp4<3IViL@!ct)382s`ZFZ={@#`7rdxajb1C^jI28a>;4A$}wPw%1qe(#Souu0@tLmy%`)nlupkg>VBs1idnblQob?qO@&{9TnCI7vS?zsDl zNC+d{YAlmf*9@kfKl=r1WN3-o@c#2rR-t)t+MZ0!3r;1flt3wr_W zwDKb&`Us{B84-Gtsfh1??}N8`yt)m)@5&ya?g8&-K_7p4?8sNhyW;(khmU;TgS_tP zL7c`S^!UkNRwyk7?>r#4QyE=UJ$U9y?H~(RKAoAs4;_1zOb4cPLd-rZ=L4sbfq=*9Ksoo22I{?D+nIb-C*7Tau55v<`DZ2rQ7(- z6>Sf@DRQ4pQ}gyEW#3_r;AXlA;lu}KRmaS6+x>Anb^n}>6xPCX9R5o{f{(dusqSi? z{|RCC8!n?_sJ=Gn=YhQE@}=bAGYSPdLA&c=Pr06sIY<}=z6-9q4VW4wB05)}nZ6fq z)Q;j1p#DvH0cLwoAJRWry{*~;reeb2G5O@FKWK01o5G$SkCYo?SuDY1od*t_`#mw^ zM4x_)qL|Ejoj0ui3-xQVaD8^RTJ+5t>~xNM^{1zlTYtG57buNSefz;ub!?%@L-KxqDGSoBpy%*vrw^mtj2|t(?yK<$4c<+{3+2CO`HY? z4f~PX=_0GcX58GGmeb*MQPSRMSy^FR*M^9@d+vbi`8sv_zJGcZjY87-rrcPC{u4Tj z_qyA}?LM`pZu$2hDil*Xsv+7#vGEGI8`+! z@Ki=|{LXruwI<`VD4)e>L8;ZR;Vy~KGt0Z>)9tWln4Zf;@9Rc)z^jPu%6P=7odBEC zTcqb+K)Lt?zpUMZs1q0A!}%d$G>udE(aY*g=+pK#{g$*rQdHHaTQY(hV7(#w7*1=< z=m_sBzHZP#@T?DUb2Fz>*+fEIqV3qtwSfC63fX@>^Qvg7-YvGSAgXcGohKC8@-=(Y zG`Mk%Ctw+yKV_bjHlZNiPdV)z!x?cb%wx7ZFQLg?Y;Vy~IIY*b=5;l)1&zc4p!7Gj z)}mol*O|nAj-JhEbqrX{=lk*KzHkKh4|^kl#B{jB4pw4c%`$&Za*bQ-QjAc8+#dfD zgK}|GcgiZPD@!>(b^+@(q;HFV=~RsnE$r=)qmcNWuPz8WxZ7WED%xLbJ>iw9f6Pt~ z?v-fQG(PkgR|uos0h6PIM9sRoI#fjX4x*1KC(CW#ePIiNf@%NJh=ET|5;E3!>0zBc z+z}GRWsETD8~St;19@umeiHfVU)53ky=86-KobLd5p08I4^vNTIj$)^jqezUe&)76 z&6KIOu`w(aFbJObvTcFoSPQU>Lye>mT3zs(+0o3a(N@MxK~qZ){^;ZBH5itxfj1#e zsQPO#J8_qL7O$w#&h$4m8~4wVans0b>KcEkXfgCTMDGk7D)j_;Jvk~F!<7VJs9bT! z^hZUekQQhN(t9uL<1wBnQ(oIiVEx)+w8u*;-B|HHA>GQ z6e6nu!(*_7+Om8U=`&<}R~HQzK-B$aL|QtzwxGUv=${*};D?3K4aO&jPt>@eE{Qwc(lfJApuy4Bigfh#D2nn8+d zx>t?o!}0RNmA%)N!I*$KLv3sOYf5Ak`RZTGmE;+c_Q!a8MhfjKxxEZ$*vlPk4x2n{ z~Q^B{ksmc;GZd9NFGab8oG;kw?j3WA)T{U8ytWB7;^3)kN}S>r2&m{- zQ@S0`i*~meJk=gW@}D*g7B$Qg-e^j+TiGiRw+32{+mtS~G`UsAXlO>*@myrt3ph_W zF@Lbmy=#Gi3|x-F)vd0lYF7^yd*($K1iIT^JMl*@#GWz;Xv=isy{!U{QG5LK;~KKc z<^!Tp{HJpdJ{GM>>h6ukzBW4U$Ue6GcnC3DW|TiHdU`0WvIhFbs69L6Xaw{XOte z$)PZbv=nqV^Oz7g(fLu}V~p%t$ECBCK&F~XW9aj$0qJol%H2eR*WRe?V!Ol01tMZC zl>G5FFR{(yY}H#Ba$FFrYV6<@eeLvo%T2y?BV3|c2Jr%Ho3{`4t;eR!a$AphptGmx z#J1~0&GzrPBj~N1Q)pJIHwR!xJ|UNtpd!idB`8ZE;RnAbVXaZ9VUKXE^K8(+kiEYjg@tR!L-l{hNH@iqTelu3$%tIN^ z+qA-KwW0c>_R@n8ckBzkh7;T-lx*47gV7;d+fIV*33eGvs@@L z?}QGv0XhD6MGHm6pUobCU~>0Dt+g3B6nx6TT^ac2-CrSU7}8Gk^bW?!c*c(22Fk& zqe?3;)RFEQ zWJxbdU9XrsqD^(};$M46F&b~#&kj}O-HF@a+!z#dgq7d5o_WW{#-`K(qLe_wa*Alx z$p7?1v_cob6~g!K^s96Qsgh*qf?X}bWz{YNH#sf;Zo}9|?+2uWK969<#yS`u|H4z$ zs@iM@DonSrpW!I1(-}j*f3&7p7T!rgUdAGY9`{4-!Qsg}#a|7oHZkqN-A`+VkZ?}Yan__tUZM4%4K^0mQ12{%+t@I+$^G4z&lfUu1L}c8zk6b3;^2#A z^?5sv^ekH%fRm2xwT`G}e54t!!Y3w1c})>64j7_gw}NNx*rqAuW%~HnrQgx?ABHr2 zHZTnCLp@<3D$Toja~VIo_=XU}c>qT6vG8-ZaO$$=fBhgccojJ=BK2#TTJD-LL|7dQ z|0aE9`eV6K-X@DThVD)9(8?(Gz z{inq_pZjhKed;ZoRMAK#GU5BUFcZbJw}K9ux-UO!$6TUnnfBeCNy1aV-`Li#NX})W z77*XeXR^7{Qc1lOuceGo38JPqeg7d9iS3;)^$K{qn}E&ODQq&asDyV*dyMB5+=!A7 z62(1Q^*qb7a-Xe9mk_Hjj2W-(>+1uXU639XYX4Vw4!YUD9{` znK+zxhc1VfctnTFPbm(`NZ#ui<70ENrE3ir#uQKUtF0j0m8N(Po2IR!S^He>iO~!| zCENb8v@|A=(nROdOrpbWbI^LN(p2VXYH$0?ZU-nk!a>JNO{QA_?eW?ia%(N5wba_cak)tc-fknDbK{1m0L3#i@qoeL!Kx80v2fCM$4w!AHTT*>CEd$%61T$uIDCZ| zd2>Tj!jBUkVoFe0m)ut&qv4?Gh0xGb#(2}84~|y&u;&}pwbxO%GE#lF1=GZ;oGIUA z`s_N15PU83pSFh@8N}r(6W7-f z5l)9IWt^KsZa#VR9ms6Rjqkj^o(Y3&NaNCYudN zgV<1~@kqR7SD&H{`PyaAlH1*?P+H~ohg%{L5i(g!PO+nmPJf{s? z+8#Rxyca5|wrnsBv26^LLm&v2qyi4IxR3&DMOy=w=xzA)%tpyPHZTxIXo zqnU>3gE-=-YaQ2Ug%l5-FHI9KESBq_9^NW}sq?@}FLInADEZ3@85aWKDd|%Dqu%uS zn>|kM<#~Bxz!crhRyi<#-`VLW%J*j=zPfBj@7rI3IyCd<1bfKSQZOzV>_u2Or>-6_ z#o*Q3)J9TC2`GRWtT{ht2eCF;?J(6ZU!uasJP+oP2?aFMK1}9Fh5M~$5oWk?6|Dsa zSE==O51Tg^K(X^VqH=I>^peRFZjQKnr{{=Z=H#016Pi>smux4zv5!6%22SUuFF$P; zyOdxRiOQsML4jI`;kSDP19yM!VG*Xi@KfW` zm`@vB<@(MP30DQ6NwCKi4LB;n0rg)OV&zseA8>M*<>MHC>t5#goid^d64-fxfFrNf zY`CBaOa+fkr$I*sM6LAFc}Ob;8wrawKXxqLR&I3pn8N9~4W4ihV^gl%GNjL1w$iR| zoEh(8(o)l-vf}(#b=Ew(w;Qf^%EaT3^nF@~v>SYw)Ey}FJS;4F6}Vf|&jtVtSz2nz z9}63;`Ul_!Q44LHlFNWx#J36-S%fGse1-IeGUKr!yFrVl6a`-d&xE{Te!&|XufmTV z6lGdf`9(H=0&24o+qZY-+McPu*+q_agAdbV%v0~>AlIvFgz?31=_Zzh70LGQ?=N)f z%ZbU4%dmqY;g&sb)hVdOd!BJZr7;%(k*V*{iyt7!FtxkAbO!FfzgMGthf0I} z3UO}a-~8dl5C z%G3b=-d$RAfjVoT1$1s?`6dTMg$5wjGKDiK@3&YiC`I#Tk99Vj4ouL@3aqi?w|?B< zv2yir8Cw;st$o=t#-sXZDjj3yG_!9-a_jzZ8BY_)f==)Fz2o1LIHXzr{=Suir}4Du=-2dwqa|klwhkBDbprRA?A&G% zyqGw1!CpFOY_riZ;Iu)zqQ*c;gvj$E)Zh_!#{QfVgbK}GTybj|wlMTAC~w)8eFUwD z9%@eQ3~T6tJ299AVDw+PTHnvl{YGKrUh^_$w~d-@dYH2>C1$SG)Q8bOf~4(l3s9kn z+!h}Iht7E&_h9^cM^(Rl+xoVbs($huaf=>0lQUXL&C;yg?I5SxRqpnK-6ENXA0LRx z!BZ&^y^&*@vG((CoZ9a&-(IUs=-)r@O$|g=>m^RK)7+h9G~D|S$6m#x=)XJyU8ul$ z2jX<;e*3|}Aimh}8gN?cT!}HWT(9x>(yxxM#`u@oI8Fb>PehmLL{_ME|J6S^IZ%)+ zv2WR#`P`y0GO@o~Z+cZH`~-oiY3Rl1I-g?P2XZ#~jF7dv6MEapgY32H9ftGEG!5Jv zJ>WcI^Ou#KoO_#=?4QCfF3{WyX|)<1Pi*U7P-gmmuCdU)TKnvn0%wcQ3h~lbx?(ZY zJky@&;9a`r%PQm9eD0*QRY3I9b@wFfE%v@j3^A4N|mcmWnEo^tjZZI%AHijgh)2r zbnU^;Lciwh<;|w%a!cpBihT935nHU%yK4_@S0an`B*`6C|pihKK$4Zo~#>r~wi}Ae- z%(4sI&#%%ZG8rgh4`&6Sx_?jrVGiPZL>0luJ`c$2&?dEpUbFIwM|jY;x`>q2(%pqpNx6Uz6S3Oy@vczOe|Zz zhv>S+9Gd6$_rAZupB_{9Sas}AyBX@hFgPC$E`CS;o;zi*FFXaPZ@2(Lv2S~kBz~1I5T%at7WC$Au{wcytO;^>q}Xvhl{jnZy4-|T z#IToHVO$)nuZuR?_uZPO*1r68x;-XJNnQ2aiPyYUGr>_5bQvxxX!DawIt+}dL;HDPpEGfRHW%jAJPHpMx~iyX)X5|>$T5a z^e)IpbGBXwbr|~ytuNlpkU`FDhc88QBoiT4>S5eFKAL0hw+FPO?dd30&MU(0cgz8m z8X%IF_`^d^9bj3y5{!<>i$CN5p4X!BU$rere}%l9)_4?O-aC)W(Fs4lKtX~h)88wW zPa7&`*@;5eUdx(KTD|A^&p4Pkvs^D9>swEJIZ%fli^T=GSEvH})LMO3frs`Cc`TM8 z-s3YqnOI$jLQ0*k=gE!g&Ak}K<9IAcfR!q|V{-P}UfThteLj5qdo_lH)(3@(NP7JG zz+Xl;i`E84F!xL5G{?&&#lgCdg2=I|Eh{&Hq4j&)I1#$7AJn0!i5Hz&ej5(8EE?s` zO7?&UviRE&9XmC%`aJrfW3jB&ZMhC@*^#QMD%)vfwL|q?h7IerGfGtm-^Yy2;J%)Y z%9ffn*ao&VQ>;Juut=~(tu$M;E=>prQp&}~#z)WHRA3^rR%|Nk5y2DEvSPFk=3!xB zOjNz8s&Emf2;=-buu9aA@Xs_8CnHryg>1^QAdLo-c<3i7aX0eVf*dG7E$K%PH2y*7 zG<<}4a{MiLN9Enl-#>*kS`%jr0}sQwqlc7fS%u$;%CRu;Wd3Z(Zm%7-b{BP%k)MWk zwXLpdSq^wc7k$~O zM1u26!5un15~^PFZc?nsbvMZzy+$aCaQqV2+Q`cj{3-mgfbT=`S23pdx!v?{ycmRj zS?`$IAE);?M*ozM#nApMA|XIQ8pXZ6 zjThkwh%*#~lWc}u;%ooXGo-J6xb{%krZGG;?MaNW*IVe#oxGIr*ERJgub{60b3AOE zsK3<87-mfjt~jii*$h7e6AnjU0euYEX^kZuz5K>}ZfhLzHAcK$kAs^0K{=uyP&s!F z0F7V0{bFVG%F#{1%(sPeGFaP^t&0uS%Qi+&0i6mpO1k^kQ?=xnjJM1|zOm)U1x zDe8Oj^h(C-K}OpJx1EmAl$q}{coi^@OoEJljt7aDw`fZaVS9QvpK`ZYXz)h9MII4d z{mvi1f-x2{WUg8ZaQ;oVRruo$JF{IP}6) z#Q2IK6hHh%9kYi%S_r?NM)Jas@Pf)&ga!CjOSlV>H z(g+ccB-+0L}*)YHUU{)W;2{4PqA6AJ>s%?(6K zlm`c~Rc-3rU#w-RV;X~79?)U`WA3fu+UmM*VG0Eb6lig$IK_)Q#f!VU1@|Dup-6Fe zNpXU^JH_20!HPRA5{mYu@B2Leb1u%!clDihwX>7#-`-2+ntRMS#!R&@*K%?+DQBv( zjUEd3@p*yCJ}Y)w17Wmh=78VQ^G*hj{wi?b`#@!&uBzLVFbz zXBF-bqSAlhSou8MnJz$d`E=qc-F^LiSF_ULCZ*;%oTOKp`?phH3QA|XNwl|FpCQ=DWC^5=a@jsA&EQ8WbB zo~=-O)xrzSQU7%l_{`+7W1!5RH#E8VuyM;zJN5-zbR@u&5{~{}w4boaZ*~;$CCV=s zoIGz_JW&J^wB@matf6SFfk$)chHjD9zg16G%hoXjo^5Zu^GReE%hK(uY*Pr!%RZ>n zacUK@l^v^M#%p=_r(xB658LQ1A6f z5vn`G=n3O!uLlWDSgIyZTLu9fJOvf}58sEzSU(5hRmR-s8zlH?AICP-r>(b)%%(W=#aP55K5Q<)QzaJRv z{_mZM_pt9)-|w_;7x_e)3rZH7oMB>`2f@qaHj9hcH6MY$7}@lC3T|U=cXwpsh_VcA zGyM*eb4QkO@6!DHD4`)&ZcqD$f`$Q-AfNJw#fBNh4D=}TzKY^;?tVS)4bTz zJY4I5Z30LNIu*@xtRV^bI2x@!fq1*>7q~I%Q z6@pt7+@oB0r5258*kaA|Rkw|+hrp^{`WPogcNcr6Imy7cUA>PwoNr>BIj<&>QG6!y5qd}+rVCg-VO-G~maEIq6wMO`7+w>C+ zox-%Up-MPvnpQzn&XrplMX8xRjMbHQtEkg|p9_>vvux-dOL|x0(jOOp?x1sv7q1O-G zZqdp7zS<|Rnv~jV7)TXxni$!?VX@lsp2UuZzn&advtZ`LDN(J%XKcabVR5=0dL0rX zv$s~G{2o`|3Rtf-UFnL{-!^=;gKpgN3IAdJA|M@wSNQX!GhH0EEaHmq`S0$Zn0AUP z^MP=YqWh}N`>KwM?(COmJ$_f&DO*`LC+FTLP)psjlFy-cY%>phi{M;1ln1(BC_RjV z2ehBIP{oKwzapmg^@;oZQVT%DUygNd$#y)Gcg#bkaGNnrVq>B~tw<#_{$42obWvXY z%}8~V9Ui60;xz;Gq?VhU%1Ja-Dh-gY(m?*W9rQtohk^W8_+VYRFP3BG4;O2_i3`a+ z4;nGBV~!;u^_Qks{!##b8%UtE8J*MRh&su<1-W+q`y}+#$cwL4m1zU4>`6=$^_6U& zrQ1Y){r)|c%Iw^JRPs!rN7|Ve>Xesdqf$Raxhhmf(^+4a%Ka2I{L4@1Of!PxY+`if zwTCXR4ciGfhQ_zq_D0(x^8#WOO8#0u;9&3*YLT;@>e-2ozaI5T&zu62uC~cjLX3c3 z&6w>-0M2A{ja*ySqV!_$ifCk{gJ>lBYW{v`Xcc42t6c7F zT(OP;uKx+$fbrshu7{p(1OIp(x9JwR6v^+L6j;j?U4-j#%IC6R7V$bHRE&WevU74Y zPdM)_w-5wZe;?1>U6XpEl!%_eBR}g+_RH`L`V07&1qZ)4c5iWj_`x%;D1^Ne(nnXR zR~9>S%naBla@GU?Jh{#D;LBt@*jzOB>cPkaU-4wA`K#@A-z{9~v<1NpCRudhMra#h zx+F2{Q7gp?Bw1jdB)xLqQb33QlTuc-lx8}kGl$>&QMId;dK1X!7`$N0=;}j5!S51u zOF%JGNB4xfxg>__HR3y5_ROp4jJayx_7rnc{*LT(FQ;x9z?8LDq6>FNsy)M}0cmLb zy#W#x>a#6=PBcx5$eMD{*goNSV|X|!iAP&DGiqpIIum}II;K^&vK6!<6r%A?&7ky3 zD|zC&s+(~ArpPo=vg-P8Fs~O?^yB2iO--N(PmC(Rw z^ly4~H(WLzo=}u}Z+Dz#t2ptC@Q~}K&d%W6r>dNKm{F5Pn3dvsEHh$^r!U6Yh(C!k&Sg#t3X7VycIpRo#Ye@=<7B7alBvOK3p zmCJ@{C`uHXE|UkQcWzS?Wv}Cw9u?%7dgoy47E{n}vCXC&D{P_1z^T}~uz=^$0QcIR zYe~NmlR}|I7G^(JgyJOUo77Pm=^{QI)ApYv)0!uh$s@aVi17_TC}=FXFeR-~n?GKa z%o6>J1xWWOHl16&=yxW*@0* z)_pI!;PNot$K@4yw;_ZhR_07Yx*Dv422Gx^uhR${5ev`ZT0@qWp>CIBI^CCjsFX$N zLL!&KT1x(dcLyL9XF+*OATY&;)R)sF9g4$;lw=Crhf82R4+lODr$l&l?vQs*hr~Xv z0p2KxNZ_Dt{8qQSkfEWE{1iLsiB2t~K*eArL0(@!+^$|mOn9Rfi!YJKY_8zybv3#1 zQOfe*QJtVz_@hRqI&4LX7;o~O*6m=Xp69ZKp&o127|~|b%k5M(hO@--lR3r#V9er1 zaG8Du_?Zccw0`tsYOq4_&b8TI z)GYSKLyu0SZk^{-d$O`XCUW+Hngu0Y3(#Ss2xtTRbeT=gcR6V7KM1Ol{-7oE>drBP z7+tHVFsw5xCiI(n(vJj7-nfk7DgK?6J8A1Cw+E9no_NFDvP65nINO|h(%XAa3|M@FQJ8pxv-ccTsZI4$P9NS?jIv zg*Jjla8r%K1|MnoLdp z2}tG2c}hbNKJkJR7ca#Gb~oUjpA2*gd}}d{=oOc@jFsaFvAsTn>pJx1B|M(aAf%v_ zT&Lr`Z_=HkY6=eU704R|yuWn_Q^h`ozt4L8-0CCjI+V7~qiTT~_1GF&$UBb?DHAwh zJ8M*ESI~CCrF}RBBXlIC0Ll%M9YeknO(Jcj@}DgZ4Du+q$=3zYyPkW#=?wnSa%Rj; znfe4n>=zz_fvV7FBssZ!FdG60)RO^Z)D`y)m32{fkt{YuY27X&PZv7UV^chC{A3Yh zd%D-nZrLOTB0{pWW_$cJU5Pf2^g6$ble`p27z5dQRzCHWdM z?~30&YI8KQe=yr^Xvf)<2H|oFcUGK+KU%U$)MUZN;$WeV`RlV+FhAoo>Iu@ccFLKPj1^bMZEbJTI?q4WzzDbRPih!eM+aDctn7yFm=7hg z>s0CAOnG(B3sRhfDU5m8?`172kwB&LwR&<8Z?J(_xqf}fgnxs6o#eM(-B;u|jSIm! z{;*X~&ukR^A_tK_+F0n0*-|DZoA4CeDI;`j7HQ9*<96Wc%%iIZ#<3C&CYLN&Wd>eL$CqEpOk+kBQfa%RoIz~>10?w_73j5To>l|Q{> z5ph`X*JlMX!(R^Js@vyD`Sk*XX(ycl>SvYjPVp?vrq0GYtPDno1sx{6r&;LzAzM`! zc3EBSLZ`Q!g}Ycer0s5w8OWXxIu0tTM%n}<%{H>Qv!B9RBhJjLjW2!e$4uO@$pm)x zY5$C!&3(XT@oa6VC&xq8b2&(FlXWBI?Z}^ftKI`Q+(sJ6-P=HT(!rO`wP-_+SJ3T2ib22$LR!AP&&{Puk06}J zj)O0gucQJ+xg~BH*E`)Z*d=&<61iMmJzKDTl}bOQr+-~PkUgfGxy1vi8(0?qrmcfs z{HyWA>X;uFxk~u>i*cHj4ld89gfiqW`3ccCyAm<-L|0F4>1GXut%g;13?$I zWdMR3D=0t^575u%A}D#ma(i~P4I(~X%+Tg#C_&+fIYk$u-LYP>TbDSDb6%z@;Gs44$B|a z@>Vq<%2^Ck0c2JKU*z#@Xlz(`%nHoU!kCz%jpL7bIGoCT1c@hrxWWu2-A#zl zv#z}Y&H!RfD}ssRS7v!itQa18q3)Seql)(4vdob7YO`ZgU!3=T75#K^ z{~Umowbx$-66$z*xW&fA)S`xsqc4n6hz!*e@Y-b-R%pjn>ayKZR>MMbS^Hhj=E8pb z=F;Qj@>kE3!Co8vu^}|dqzpjGWu!d*^U3j*`?lTwZY;k193~01?ml(@re2_zc-81F7 zVT6tbnJBp9!)=uu5$a8~{J0GA{uL1#&DN^jzEv6%9UuL%435$>Tp-_kB#uNKO8hMt z{JYuWTXTA2^SJ_)rL>UwtVG5f#r0wqj>U(a-vb{+aucE+Y1aJ^^I4{Yb%X|AQhQ0* zq6n9nnYDzmF;A7rn_@wC*IF%XB)^znuU_%C#vve3C&%Hz&>o`uXK7 z!!YI-U98O~sqFrY@4;mg_jHNKUWKCuQ1h*trSl-$<>IlYULroU9XCy2w41xq31_$U5DDHrbw6=(ovjI zoM;#pOG}EulTopiYHT1!!G59829Sz5V#})ot+#?Nh+6r)maAXwd`K+oLlz?eA1;KW z36I6VqSK`uUo&27nCic3F(U;qEG|)r6ju;%;!lA~s;OSF5dZd=`0}YCHGGTClf~vr zEZ^ByQ=VoyF)Sz`Ez5O*vw2+#fp5Eu)r;Tv?AO+P~+hfjR%0Jpe;D?L06Cjl9 zRinc9&&KgWQCQ>W+7e;1ZkG;Ca>>W||79e>(*PgSn0|mEOHfj&Rsf#Wjk=MElmmft&(dCewVi~Xl`H$s@cjDaZYMd9(Y9Xg5X-Dn zsXF@piTH4mVNH1+Gj3Y7$1tOqw?3*}e=6QcJB!j`H67LCx|8thlf3du@ml^Bb%vk_ym3F<-rW`~2=HG}XA>-84pm`?wrSg zfak|4Tds%`d{&ECS7jS_qtep`5Cw8{-1pPBNzNR(n^wLh?r+H)`#D)r2skxDT~oQm`E z5Grf=D%?Yh*ZimH86Nnn-`5E2Q)vdc^!ltAX)OOpg{bleop{pr4Im1AVwONBsWvB>|crp-TMJy!zDQEem{94I4<+%w&ljmXv<_M&+`_h8_Z z-afnW%s|2#o8bYsL!Q;clgMd4w;kK);7OgqI=l^`HkV<;7=8b!b920Ob+l~ZY7+8WFxc^4j(4H_>~+^k`%~bmJ44jHomsoR*X|aqEB{yE z5`76jpp?{ry9Vql!0t=jl&>TcTZovvx0q4qyo>pS zY>l7X$v0#9S9Us-_ja%$C^e#_!T6x=xc+tHo#cB`tlJ zWXlwD$`Kg+KCLe@ieN-ykd*ebk>x|kDh(J7dminMYCmRWV)tQ+Qa)OY$-no zhKCO6Jw?*wZG9_!Zg&S?4we5FhrdLAj_yqIvq7W7#a|TGpZ&5ug``R*N%Rb z^~Z`x%JQH7h~aFSM5vqexHDxqF*A%-3cy>T*MTWddUGawRWK`RXP|pE9MDs{8Hwzy zcl4{bHs!{bXn!)c_6+Fuy_^X6JvC9Eo>HMQR zT`0ejWc<*jcJ?l)YGBi6_ae-z^Xc2VKP%*F;B-oot2+x9*Ow*G$Qi3x#L0Q{hk+ar zChulKkbCRAj+NhWCU9W))mWzGE>n%$2j92^A~+kFo3h@G8g{i3b?Js2*H)KYrxEsm zcMe$-kXG2r2pb2yg5Wh7=p0l#>1G+cm=n#dmz^ce>JYKW&feXK@6V>K_o_JE@OpmT z_}K@_{S^y$y42#r?DmPb&Mc|^$!9>QCUk)~8-m!z}1~e z*Y&%rrNcK1)0oa}I;Dc{@=KL6J)~7=&;P7*$94&MS>(Lrv}E;eCf`5Mz%$@rS|N+a z(Cc@y(r-3%W1Djz_q{2YQwJ2x_#;NQK57)`vb`O z!c^ypi$4l)YP)UMxlCkRWE@78S0^9qoXgB9J-V}n#Ru&qT*F-}Il1ZDPzlMbR0)g2 zUXrbuq}eQK9}D2LK+gqv^7ovuooipHtgotCCIdm1EMLJcn$v z=#*C0;<_o4jsitmCKzR=sUyI(On3SrAx2AF>Q{iXyvp!%VN3x=-xbbnaD#`Cc;dc&b} zN7Cfot#ft^IqQdd-B)9|^cnRfTAqLd;ALmWeRG$kJ;+T40jlEks!T6s=BZRjpsRJG zBy8PE=XUPI>eR2C@hFL4fos*QX9q>_!X;)eZ&QYsQZ%}vi`8$x+&>L72|`35nE&)` z>}e)nF^hSHasun&(lfqONd|ZoBA|WL?0)$87`C*^nG-1V^>!mW%#GW`()aQda;NU( zJj~=68VuF{?$8v>P_SQw<^eT=X39TL7*+d!YbVd#ZI~U+#Q3p#^qqQdu#@rObGEDR zLj_rP|HSx(vigZjzyA_(_61sWn9M_qB|OAEwHv4KW5k-koiSG|DaT>3`UUeT<9HOr zSj$T&Mj@B@u>KlKSU523Av4B(%%bkDu&{q{#fsdKC7oR{G4cDAheV4}InqMtsvwWtbjo;DZ zxT$T;CtiC92@Kfcu^7l6yz2f|Ui|Zp$)W6A3_AULmydIV@Uv)1WBZ;}u*^(T6&WOetT!LUnzR~-#g zE*PMC?huB*aVC(9{o;TL8zTW($k*egrJ_#b^mJlP*ImFS)ssNJ!}0eHAVcXSRbCLt zwQ|L5gFqA2&61x?!jw9~OcUnqRMUv>$2;rc?&7H(>Cv>~eeQKj7;Hmtx9ZB!BcSt&JO13| z@esy}VfMIsmhJDkQqkxYTW7i)e`nEsqwfn5yK!H{Vs@Hd8M?Jl9$PKp$fKO{Gekyk zspM24-&3E_{Dz6~J*1`gs3;Aq6p--jx1)T^9_ql7_Iko8#P*r~Ydq~0q&(h7K{spS zw$Z5NtPlUk)rYqwti7r7R(^hK=lZK?Txo60(c3w#B0-!4ZhVluFph_g6!E8NtP_>5 z7WQEW>-!j4+1h$vCB>(xNi>nt?UpGHO5SAVp zBK#ll7K9a?_y$3BCpwPql!ol5n*iP)m9jn>Oc|) z0s)pc1vc(R$)(K!A_77j@+nIGHC3Di%ug9_C5Rkh1`T5h(V;Jc6v4#-;l*nN1oyAd z!U8X31mL(C+LqJ0@>pDY@s8aV&1N6D@6?LBM^7Aqi@RX^w`XhFBw8~f^|N0Qg}LOl zK^YgfB%v?((?0s5AWYzMz1mvEbUc{x#t`B_Fm?SQLx&&NlJ_wJC5}~)khURPRp!2T zuu7%o3o=4bHKQ@og!e#ezx&t-!yOg%aF2(&%%z8+wVIz7-c+;ib<^Uhq4224#~@a_#hFPRc_82KC( zi3tUZ1m1xz&_a|03^F1aRitwDo6yBSi zE+#6+d~rMS$Rex=2opkbNn~d%2nYl(BK8p1BO#s|hnAi%mO9(^T#j9+bU`x|act{L zcM>*S80bmeH$J(sy*9nQ7Tq9r;T}_P@S7QgAmu{{Tkr=m1O)G0!dra|4i+2)1Q*Mo zdw5SvEF-qMQ=SiGR)kN8wzGulyn-O?Coxc8!Ji~UM0<1UFo`gnY6%JH z?|Cw#cR_uK$P`7UYN}+V8LtXOtM$) zM;WTwzG}NH-#_ak$O1(-=*2&mW#(yvG zQi+K1KWmWg#s6N9|4$r?(~X$-e44*z1pITm@F6lVeSz{%*VNJmA^g989G%3iluRoC zX+uC@p?~+^aqTTAioK_E^rLl0M9^jVXYK?^qiM1sd^7m>H|Am7E^l7S3K7C>AJYG0 zBlCZoDY_{yqf`@1z#``X@KGWByP*Et6cGRaJ|_5Jn+2H`e?vBygHZc3`2R9%OetJh z8*^Rwwbz_#7SW>D%h$AWCkkq>`~%bV@2@cb>3-esv~q5Z4RD*s{Xc^yM-*N6^EcuJ7QF~a$@aycVOaSUfN_0!T5!=xX)me8AzyJelqwk765pX{AXd-1|1sq zk}2Pln=j6qdxZin5vP|>C_!p3npM`G4$Q$H*r86CyE_%+%1)p$ynaR5yzrJ{-PS|r=f*9(H9X-y5E{8CoM#_^2x&39N7N;QAtl~TTH1FjnUvR_(D zdzLq0+KbU0cO|i@s8M{6=3V@OJ(jIy0TB6x$wVV+BLPmmN0|q``+DYa=bb>ya@V<{ z1}~U>rR;vV*Yd@EZY=`l@*dzg>R?n{b)4nCAVOZtv)X%@;1O zC+aQ>FiZ>l-;b2U7-iFH0@f^FwCi#OuD$OlzS@(4JTB0W?XN$sK{WKA9Xq&e$tTdl}ZXCJXB zZ{%U9_i8|j;#0_)hh#Oe)kUg6j09bUx|YIwXz=3VYBLKE=eYIJjOab4;+_1SrBuP| z{$spcxr3-oA!>cTka!&_?fyN-i%jQOWaBC=&n2;w6r^ml;a#nysiacq7{5pe;f2fK+Y$8HRk=0ng@K_E91Q54~qM-2+BoEG2qkH ziN?x6ZQl8a(A%%*IW+pxEljcpuf#` zwCaHgG^?AXeS?;fyeAFjfvH{Xh;(LwK4*t!!?;3kS87ML1A^fSmFLnd&rbrc3=_tV zi^B(Ehw~g9ZyI_linYg(B$dR!(XHY-VI^U9*=wPrq!F9Ei6 zSjbj1xENUh#Na-mr&tSOV*a-&v0u|IWy%9m7U}>hOt#5{SM+kZ?zE}3&19GR-NBrx zqmQyj+(&NrR)w?QUdtz&zL8F~<8p*8+Tr4Q=n2Swy4CWnP`im_01=Uq#V|#(sN!kV z-$cskU6pTXW-^VJGaW|l6VR^8p<6jBOKBhPRvi+zoi9b&kzS@D>u=D?x!c(#MSYxn zhh72vf!;QsEYUpWO!~Q*?&~3~V5xqw53>vH6gr0)10s$NouIY}TYV;P z0%l?^X3TJ~c8sUIgaM}&QltAz2N1kaC19Xvv+>VvL9wgEo*n&%>`(!6!Ti!v*$h2= zgM^QZsq%V@cKVe@T;79G;O~a~fjovda zF1)>y06AN~QLkQBt(O@rQX@<6Pcf%=kBlO!@|PG zo}Up@YD6k0`^fyu^vUgP21Hk(^c}0d_^Kvk;jOLifgm#0bjsJHDB`|1!z{x315S?V z<3#tT0LftHp!J;E%8_i;`H8o1J%bn7-~};>Y(c2+o#4F*2DX*TQn(d3Me3cjW`mqn ziXG^?OO~>t;!hL7*eTnkVyTOZi_-b~`+MdhmrssTwtwnH!B;5=T!iW$+Q0NRG5M-> z;96ra7lI$Df3lw{?UKrqWTQJNBxZ@!p`f4uwHQkcwHSXy*(C>m7jhzRaCCx~NU@K- zcGErVw!ipf8s`$;H4l6blwjSd5}>$p6(eQwSIW(ZDRnI$-xEZ{19UX4Yt>ot=rHcU z40Uz$`oN2JZFa7jE%V_R#aNayGh*ywhETRExU*JQU!iPPfl%WR zl*eDz(%8zAS%DR4MUk^RZk%bBh~f~v9M>b8CXWM&f~9c0+E?H4K%r0tbSkAHR#!j2 z%dNgIUyugij1Mw!5nM-kPDe%bj+VTLOIB6~6C1mRNKaWz3~0(uPMf&2yv!%e|7qLZ z!69aj8(Af^uCg5xd9u1vKyI`Pfohm!U7{Ok_Y}>Y+_Xo%tiH(NFjrsol{BO0=@c4C zes`?HN@EQRxU+Yy+J(iP)PLo0b$GrTUrqK9lxFtD7@f9B8FfgsrJy?azG2^?&}{z} zzgo;aQK9Fgoux6{;c`Cz8BoG%sh+CH+QgR93~6{eQNoXOsA{iY@+Vt+G}t4{x`fnl z&g+O*un6bA_@50FE_9QXkwFAnyIP$N@ch%aK9;GC2|Zn=`1{&t-TBaZGh))%ToGZ z|0SygBU!*d1Z8#bc8TN~MCCa-P43 zX&`|;&OPLpBN04fgE`NWgU@{RCRgi)8~PH8TfxV*skntrnp`8a{ln`W7Cc-Bf zOp{{)ZZlk!j*i{~Em$y*sbd1`cTgnh2^&YDnZd!9UTN)+)ky) z01EM&vY*SfI@C^Jhq)1Y=VcJ(-Q1|;UP$s?Ttk9Ax5bZ@d)@l>DCMa9Mtpr1PI;XS zUfginO{PgepHj=pmZkQWL0hm+E#K!pHxaj`k}1ZZyC@jeK5{L7l>CZpxr}9W;r@l_ z3mHmzhM<`2FAiRb$&1=tfYH>(*NT_;@E;xC13TviSz8cq=UOJDED zfNQN%s)r@F8u4-qb8=Ffg9%r&WcNT>S;rR_lw@RN?Qc39h31bZ7Ny>TcNEW4nN1ow2zS@?_x09%+;ntXKD)E> zA@|^ChPZIBKKJr`4E)#jQWxw!3mSnw%>k0QZ6_3W^m#(!MIQ1MvNrQ|NZ)?$vja3x z-Z=gW=%HUoBmZnLpSc#zzksz^1_ls(v}Jn?>{Br<9^y%zfob6g0Ke7SO--BZ&sun4O#Jz^+0o) znG>QIW+gy3NJtj5P-6$KdhmT@087%l-Bv)o?YuQHvfwAp&dUV?F|}+Bcl5}y;(Ola zX^ej@OUj5+P-*Gs3u?1RQVnaZeA!I=4}t9h^CoC|8Cmw$SI-b93t_4pck4kzLEz-bH5&(C#rAMVqRO&EnbRhyf@k&%+{V#do1*^~Rb-y0#mGS-Wb zbHp8Hr$1ok+O;|RiiHjHVJr|h_K{VUiw55}faow5d@a@h*mx`sb4Oj>J~SFntDf+= zC?TsY^-*sR;R`H!SE4BZpmS;#`xgrkDh{EBCnv<98c@8HKGPV91TCER>=}!U7=#s(MU|WotLbg`lk|CC~O^)$=)UyPhEuz5>Pzzv0H zc!`h67(wM-=#^HPECs=zsJl|@gp)!$32W*F>4CzF9#i&7VJ;!O$bvSRife~ImyWGU zMQj2sQY&WKkFtnS!6`@;HX3TX)s#dgNLm(h`lpH;V+9-)n|sFd zmkwiANxY7B?c~Kv-zpe58}ZXm7=Xg`yGC-^at`j>OZgipa+dU|6IovVZV*Tq|5xc_ zVc97hBnE&tNmR+&j(%HZXdf30?CFkE+~3O{(iO{_+`vK~@GLAWvRm?6bBK(U zLzXOA_V^`%oX#273wfpR5@dmUJ6A>7$F@NyA~G2{g)aP=cnV#9|9otFk1?_6SY z1enXVSRyv=_Cdvbd4YRu1X}adT-9$WE!H@NlN&tR*bUj35I)-J$zA zrQ+Ugk;1x0moUd6=blF$YG~RTOat~(Z=g~KyL=+Ek|3*Oa@v|LE4$mbgy+~thj1zv z-7T`!3axNPN&a6PW)QVzG3A7}kfZVwT%x1+j7H)l2eKz&AB0 zdvzmN_tDDkk_J{Nw*(!s_8l=5P4&dT4BrKPX0_R%(S}+ibE7SmABDP8pqSCpmk!;Y zZAu0n^}zKQlN!&rR0E5d%(3DsEv-~|qAX@jDwaws9$<^5CzpyzlR&pB?F!h8K;5e> zw_JMm(bol1B!@WU%{qFpBH#zB-J206?9Mjj@s3pT=Fc8p@4SnhAmx#n-Ipc(r%N7zJ`rUjK!Y(9@yMQj>ZUF$^G3@3lFu$QpO z{7|u2AiYl5rOm6P7V-gK_yg!!^PS!}0?JB5~G$G!&P0fao;B~#ccR#N5 zh)%L;7O*T0ef2g`+iw<*)f(c24IJAi~-kOzELP#xi zbI#1E=onki&jI)EqE16Isefm>vKE^?D|&dY1Q@?lDW}E5(5mKZ?v~e^nr&zd=eb;p zrPoTyVsu4)lZQ2(_JMTXH!Zfba*=qT^`hYo|BJE?#kD_c-F*$2Mt4*vKFSk<)_R%L zERSs>D^aSGiz6-6GjI3TN3wG_Q#J@m|Qr5y`sH;;YI}0MDyW3bspDm zg|*djSFa%Ph(<4K9vrJ4fyphP>ntVk2Z2e=_$iD*MT4%yX2f^4;|2;%UIfUHN9~vS ziB2plA%^eF9hvQ`x)hc4aJpH5s#F_lq;ZXv|A+EGx?* zkMEdU-r1OO^A(2USjqLS-NJ-&XHJqe00q*RhzVMfNAtD%BS0u?64R z(2})oLq@zBXPloDHL_NDxpLTY%7IHEbW`^-U9mA z{sg^a+Fm7&J##joBunIt#xuNZ*0$Bc(7&v7sRA2VdCa~b8dE^ zQvTW`sL9XmbaZ`P*1(pyYHxSRc>FnebO_-jOPMnh|3^;gobFgdcbY9*nY-} zg%3rksch)XH^3~>_*nAaM=D+kmE^?4VC}*#-&@hA#@C;3c9T`+Jaj6Fh)GC}FV2W7 zZ?y1{{F_Evi-y4)X>G+u(RixE?O%{YJCtWT6&yF}co)J{CImNVaS`MI@3B&~c(u~J zysW@6v@90(4A;oAI&(U>0J`$JRTSfS^y?-0yQMu95hA%I`BkNIB}bsZ4|OJ%D}mkZ zvYUzHuMPXFZv+n%7!LSvma9vt8JaCNb%ad>hks_zmIdFvJ0Rg-@GRf?q%hE6Ov&bt zg4i~!HZq%EA-+hT{gcGh5z)&?pcdu7L3I}WQ<-l}5SRHI`KHz{r)fHt1jD|~7(xl@ z`agb)))+(;Ik;9E>hD*^%sT@tFUDA5acq@uqT{|*OqP@RePSo3b5)=ui5)s$@A&Hq z(AvTwoCKm0AL9;BN4Tq7wIsyPzv94KT3ULeRow>!$_yF0Xe1X?RnSF3k5)Xerk&I3$}68|4t0q)bD?C zw1=>jl6aGODd`S&*(zAAb+DxDbr9#p$?1p5MY3z^3r#GS|GvVAd0Orpjlh-H*nm#@xdP0}>U8{2Br z*tTukHX7Tu-&l=p+qT{BJ@=k-?)Pv1-FrXJ%$hYbYk`x%@4I|OFzeuE{39?gJk&-} z-laMJVpDb-KQg~Wg;xV&v?j(oftA&+P82$f`95=t8AZUR(eE>ksrF9>&sH(^3C2ng zvFe5yH!F)N*tFa(@s}0!j!xH6){Tb}qh!^7#x9z<>+1&leCuO^RnDI72o1@ZJyVZN zn|U`&@AjFkH{Vm3$M0goX!fPkjwpRuYSmaQyf|y>XD5sxk9`)`NNB$DrCWRq~O^rR=aph@^qYT+3&lF$HUJAFWcN`Ltmxq_De zcDz+hRk=})tBvCr#Y$`2@H%0t5Qh-^)@!{d@D)5z5PV8Bb-&X%>|5FRjvF}akeNyW zg-W4F402{aOMHY;8=R?>-aE6VCJbnhQUAn3jBKFEoZZ~~&dN$QuU^l|!XlWL96j}& zIx*(XHlNd~zK>EvL_q^y#a=_8WZcJ?u~JQqOy$NIvVT<*3%}68=xRJg`nU7Ivpt4! zvJ0(gt6D!bUD<~eS6km&McnZq1wS{5%Ga?GYUuvSB5A>WuISxJsHJ+mzuSSnL5RQV z|4Ohp-2U^y$Xib zTK4|gBMofWHcC{aZc@h9h$?o#4UFEBLvx(}Xf>WLZvY~r+}|%!MF|IZ&(E$ZR4U)Y ztIi1U*Q-YtjUIX z%PMb&dE*R<`we*b^G(g;Y1D@3V!!IIy=T?xH?&sov+qfZ7r}l8ElSql{9&8TVho7m zSsDX6#Bl>}43vs17mkq=CeG)c78`>72Fh^o$T;JhpP44Rj21^w*P%Du z;`O|&hIxhgdFFXFlhVJGBR)-MfOra8AYFPx+_D&dsb{Rq3F$cNd3vRY^51ke%>X*9KKn5=!*jd4tbqp>~=eu1u6`DaTaZpymFa^bS|)oAcAgZ_3w zWvsaR9)TTFRqZ%NYbK8Ox>9GJ<~oov)1+qK=cYX@o$)bT`3B2)aye#U`l^Mb%~+Ld z+!|>fv`mU}`?|TpbNF3@*UV>UKJm4jY0-Vr`m9Yd*(6_=lHWx2ev}AQRq%anvTGHA zPjsGAN6k%wC}ShYO%|ABLpq{?7~O>gliZtsDHrjZF}ua4e8p!CN**Ff5Ug z$-K{?eah&5KFgYQoYCX1F#uAlKfCp9&p<^-8YNU$hgQx{EAcNg&kwL0Z&#TvKcWL6 zm8<5g$ZOXe5}TCe*|a-eR7CJUkI*X7Rx8D3NM%ms1g!;SW+@wT8VVJ?e!CZN>99~Q zLeZLg9+565E3ff@!e=*2k_7EikNDDf6lK+)c55{5BxogYO31gDlBXO!6uDp_yA@OD z=~J$w+2j?Zno;Yg6OUJ&4$E;Zt!;HD4Y za%&m2&KPgD#c%{@`rC_mS=`T?EAlojfM>|W1Tp&b-)yw@iR1y5xn~=tc!%z8<#PVT zqu*q?s_&PVOUTDwrl83gW(ah=$Wz%-R4l!w{vfJ{u2IRxD)1XQtB61qvgy5y>J2!) zh^48dk7y6N3)=`A1vMpa_aHXI0~khSzrauqJF39bOezKtqeB7^*aVO;)f%&B>tWhHSv&UurW#0qXzxixMYR~AI` zb0?cj-l@B`qc*vz@>aAzx@8rzy6k2htNZd=*z%#AjdoA0R%8RgoM~^SdjIpow@M5| zuK0x+j_8BXjCq_{sj=nUZii!AqL=En0jazRg~6kC{JUH2<#fec0Z`fiq)K#3 z!<-*CHdZl|0W4 znz5%V@e@N}z~V&{R-$UNwtPzns=W@@w4fSRrP%*m;5XDzo$ zhEPBI=7v=Td)ELy`n%^CPLHPKW{hIo+eqDGM>>ZidO;|i%}yBtze}sZm}sx6M<^mh z;Mp+!;Hdei_~*qgmYtfsLi$Nop?f`b%PmlAOmkbtb6fK7i8@uVgk|H3mwgNZMuiH_ z2;mm~;cL#`dDrzgYL(x4<3Am$${B#96QyZmTRNHKF3e2s$z9<+Q`!?+HpeaO_^H!B zIWxs^4_fNoRa~sntr-z`jT51ivX3)$o4W1FLlw}~G7pYUx|t1Ip$>0aot;n~>6*L5 z;})>iZ8*OyN;Q?UZA)V`nD;K{E|zg$0?t>n;P#6C>=$i)WYG4ql`=J*OnE*8+UY^r zzpoA>d&tgvQj;gWi?d1Rd*4I%7uh9YP1E|n!@XD9-nUGmk9GZha&~bbRx^u4hW&=3 z3NoL@cu*G^v)8w|CD61tPt}8;2|n9o#WGBli#ag59-_){!!bL%uwUA-*6{9Jgjf#a z3uShdG9}uf9?e-NRun>gf%g|(2?mlWS3xD|<<8seM$)REr;R%AhF*$#XeLr*;B;A$ z)z&qWOMPq*>h+tSlFDT*txTkkhpY{%)@aH&=2&+maqpd}7VfRD5ufT_5;oN>EOl^7 zv^uUKbMj+}Xpo*2j|tC8s+Se4>CV$eLDGX;vy1f3sHn%CTX$%^5bR~va@)+OGIyw9 z0lca!(@M*W-eQip!s1ha6%{|c=^$RB0o*@<#@z8aPPj4Fh-%ozvj~{Uh59D4D`U3* z`6ysu2kA`f7GjwxGC|I4GB55h2z~ew@x%dIcxp#qEzdjr3{3dm>O44UB0MtEIy^O) zLZZs8RP3A!kBnJhJ_}1<@O&{qIw+eR6x8Nvh&ec`51Wji#uuJ!1-Z`1p)(Y1b8i;o|=!U*jzgG z+A|n0kq5a?D zrcDPJgGpJ%Ooy{<|NZu3aB9ct*xl>oN(@sjtQz=~8c*|{h`FmY>on~d_|L-%^%o|W z)G`~*Hy{tv3%Gg;8-NF93nli2q=kb=iU*%Z-2ESu%k?x`&Z^t)u`;jkkF$@^cu@#q z-M+f;31UIPb)r##0ymsh#%MT7W5NUeZIwTMaIZv9!`=^Xp9W3!^?!bKGo+SWjT0L! zfZPB>1@p6Z%&$K5UTrGNNVG7jQcqO!cr=4;Sekp8TPt=}QdZtzQ`GT3?NN(rjT%~!crNo2}`k5L za^%>;u9@1jN6_0GZ`UNC0qWiIG3}+Tb&nhCF?1o7;>ZBGhhJ#-0weMD0KW4&!Ri9WiI?gvDt8v4VEhbt@gG)G=ykqj&+EVa5 z_~A*2L1b2#n12=}tZ_*M3IfSnR3_0guwrv> zjbzvXE-f`F8*eEj&b-!gWn85N*rSO5r9r?QFtf+Gfrab|O8FJ~e_TKHS*i{f01(1n zcRw!$x_nS|C{g_V!XNm=^E+3G$u~jDsk#iB%0EN=Zx)h5`{$Nbr1mtauGp3>>$BWP z%OR3_)X$|`f)|+N35;7sBUxgFlc@_MUW8cLL@%C*2~aojP=xmB0~|-NYQKrF1Hc=~b`~4o&JQior}cgg5l%8%BwdH^i+; zHH^}Z;65g}ezC%BUK<#;or4yS(wvHVLWD2)Lh^lggoegtHU@Idf}&0DwKpc^^4Bfi zR~dHtxFEUt0Ngl-Uh=7@-mn04JS-nCI^n7$in5Ge7LEkZWSF&Tw9~T6PuTj2yQ~^k z(m`kg*ObhclNp>DvcCroZ#j)l#Dnu3gVAx)kKQ$KIZ{5$=qmYQ{c|-IRY{Y25UxqC z2Z|B$B$=)aXI0av|5!?KZITVj)3QU9s$1PAIME)(nw{DxJX?08Wx2^uF6E?U;nW>3 zIQ5&`uy2qG*rvXSwh9}hFfQO)R)U%2_cI-)MGFRK6}YZ8TV3^aDg?zoB|k; zO47=q!q4SUQ(3-Q%|a;xE~OINm5C9xA&^JHs5OlS{?`>{TqnntBENgoW071@a*k6m zu|x1MD6BgHF<&%beT*z;^u+=wFROrV{o2iJzX8dtl&)&*6x2eNY)QDt`)5eBOD3%4U%-b-<&+~>7#s{wq+H{RJ zZ$?Azp0^t>@#b$z1f%{td}TR_N{Hg$QNO&s!CC1Gwr0#R4u>ID?qOdQsgbv@GE-kT zzow^C7|BJEVvEybviJI?*5z5H?uyJY4U?xsRTRi|i2@we z(8al?zm|%qCGJxguD#Qs)vMV=`fp%RoRXBSF#)ENUHPS0u-)uwjK^cak2R+&h$dx+ zx#GEr{69xZAuyArhoOvS$F=$_tP|KjNMkovs=4GxSi^=WPcdRAK`udqYgWF^$$5a0~9Mq=M;m$*esko;0XF=-;e1xQs}*~$_zR;f~W)B#zQ zrJRhomAu*Wt}cy624{$(=jO3PvRXEI3lb8L_u(z6HG*{HV0Z}8C|FhB`h%){v)4@?wByewy9NXT&(E!z zAtRd>@g>RYqoOLq1}%BA+=oXMz@5<>nbPg<$Z0W{r*c?!>~MjsNr7SNvRXLh&5kAg zsWWo$TI5%8yaTmmxN!L_A=gzBR75w;GY)Z6YICpveVY3B%DG7lZo^A8b@wmyQ*u1i z_L$%GqA*&A{^0_kW6Q7@&FeTQ!(rFC3$4PqMob7es}`yn)7P3RP)o=DoUvQae1UoC zfGm?yw}|8x@}BBAJsUZ^E*B#)&zPt&+OW?l8i|NnGo1?UE_B4ui^g*X~1LDZ9Mq&AFC z(vr%3*~$2}v;K}PSSOn6aSbD*YdYg?O#z5UM>v(R}0 zBGC@jtS5H<%*gqftGF~OAzeP*lhrvn3>cNg&~LQa+GD2kC~K3@51e+=7XgjIbCnrn(bcg-FMudaC1ww90F{6N$!Dctc>k9Pqb1| z_T=liu{K&fmE;g0>U;IG_rTNq>$`q8!|CU@G|lseKG(07F|6Jz;{RryNzxUjQ`u;p zIO4;-T2Z6-5N0_lL-&B_atiweigApoyvs25^Q%7M>_jE>Ey1P00kCPP2W}k1;9k8h z6e0l%+t-CJ%?+KM8<&qdZqE?`A4g|*A~3HaLX4^7#;W9krbU`_u;10JGy5>g;!DyP`dmrrmj-m{A4jr3rR=G)rK*p^5G)nxWVG)4@>ZjX`_`X!=?t<1vQwLuZp#l-Kd|_4gu}zzXG^ZHwJt_R zASpL$+nc8+oC_|VmCf~aqyzy&Nu=yUYtOR-rs#Qs8Pf}m(^Ars&h+1Jz*bVAzO}A7 zGHv(ASlHH>*WIJB+O4okvU@y1{lHu>b!=wK=yfg-Yn~)yp$ppH3Ay~KyS%;&8Z8B1 z_jEMtQNIFqmAudu{(dc{*?^2KQ;_<`raotMGmcbPQznDbUI}(^4#o}h#tb!&cJ$u$vX!$Ou{ zD6ED#8#{g&66a=l88@Nb`<)B(WA9=;5As2=^+;k&ou#hp=xZ&eS-NOdU)E24Y)RToEIfM^ zy(Ce}@sos9NE3mB@kYX~m5FP~5Q#=4<-+dUBCz^F*>U}ew@pGxJ^?|aotQm#Yk0@a zsKRQL+Xm` zaGcfP7Lgi{L4f>$NtRB_tlZ=t=0jn^{}QVhq|MS+Z40VAwt1FehQfyx9y5JuC8d)- z0d@8xtSh})7wLn%Z~2kDIpb2I4D1`oDiJf>%F+-W3p3X#?1W`*v|IMJO+e=UC`6=*en3#wkXh7r9y83MeX-@CUU zt=Js+b{ZFcn$d_HH1IJovAPIA{yjXlOu*L!!f@Ih@IjzvsmUy}r)l&XHOBZ*N{Y~q zpI{+cJrynaSg_m{v*#I#}9^w1&T-%T`<*WzC z*ePo%rg)e%UDK?dk(Ihxns6{E2uTo)CpnK*<4AJ)EF2VSK0$xRwT2>vJV-1*v?`NC z0|Juk%E!{rN-)o7DgC@o#%rDcUk?X$c-v6RPqV5&d<81FbmOj|63@-_cO!g zCH%19S+^48w}$V^j(|5=&6{T9B<;A6fWjF8+x>zZQeIxJfuG)OO#8xsO$T{#!vh$l z#6|DFTwYyG|CZA|JPgP43Rj3sVL%6 zf^g|a`$9M?Qio!!jL@tiRRM-!VA;1RF`=BcDVY4eRt$c~H}vejw8W8NUq|`|AVtCt zIFrr;J>F3$211MChd;f>Gb1VgzjMNWdBlib7s9erc`AVL`{wL98$Vk$R%7O8{(#bL zepgVFXMPEH&IOb%S#iW$mE7u~mnd*sy`AVIl-q8yxn~qP#L{k>mP|~pI;?qrh6M6jhmt0f zPA8tjD!djv*~W>^UP_~HZ6#ZWVZGk61n^C;K_^;QGGKU+GbuRA;mfHPOmG(}@S294 z%gQ4Y-mA4;(RsH0Q#6K~z{n$%J+Cd0H7R%2u30^ap;Y?c;plBq>6BO@-b;dGdVWFl zl;4bsLV6;2fU#_p8ul=*=akiFQE~nnCXRSGkdhVaX6!bGEt`58JFlEZfk0p4g1dG^7bTaZ-NFjLZF7VmIv; z^XjS9;yx3CM*H~5<(*3(Cus8fNl5X7wLj%rMmY@a8rNW&?U+&s(i>uxn}_Id8}h_BC{#} zghAUR29bs`UN-`s7um*`;aagE0{MQ#^XXvI=Y|L^YtHz4G7ZPy7b$4Rfxn@93}2RhF>f^MsosX@kwSkvdS(mKJCDsUq#jiQq+KDE%(r|8k! z)Qyb**|#%VIG+!EiKZho9vQkqk1d^($h=8_RlC{o`05H3_I7!>IR5zz=KF`-#_5BM z3|rHJNWbSCQAJf%=iANb)FVi5@e}ohF{@TWn=Go4kW*`epT^5uQz6RJDNtc<3%ya+ z4SW{~TFZ{wMSN32g$eCGGC#CeKhGcU%os|C>WWA1+Xx&@KAD`ME|ZmWto=X;o2jAj zqXzwryk~_dM|tW91Dmb2Dn2qVQY&qASg#%R_*#hhO~9q)9c$Fw;#Lx*ZMmv~0k5t{ zA9(&)H@QoK94^o_Qap-xglbZ0F-L)QQ6G;8PYm#8CM6r!&&L1cq*yh*cRE2gb%bTp z18aL{Yr@b~CGhH+bC7i({qq|&-ak_$y#mzH0i^DziUxJQirAFQH#Wh_Fq-WsWyO_0BttPG9e(!x&< zkuT~N5$jLvDh$)ak&xG<{SjD%bPuV%+jd6vEeesCTPR&yjC5enW02jgEEfD84}o51 zO=G-uh!?qv7WT5p@AxMCraIF6wI}ha)-tz3fn}b2o{ea(VOG0jYX`3?^+$PC`9I%5 zSvOxax&3I-OX0hY$oEvQWTF#ESW^N%F-QTV@!9@sSDx%iZnx^yN-Lh|z}AxDqkES4eZ0keo;LFEi7HCOWh<3*U2yM*G|x z=^Hj9BC!V`|!|(oKVqjgK+atj zK(#u!?@&UgiFeL6u3UR!@v`R zxM+ugj8A=FR@?MUe7dq13e&!xM+Cz$8Tb@ZoC63dhK>uq=q!v0%5)LFFJ{WVTZEam z_Ya{z=(WFontph8Kzc@3IX8+>rQSdlZDDmT0Q&W?l>m7`iD}k+LNvgU&epRAiuceoxx{^Mh7(p}D ztgTNX#46Qr+{{qG0bFxRevu%}q-bjLSs+BM%@a@4Pi3WRXQJ0qdGTDPHA)JMp6oG7 zG){cpJT0>pF{A#e%62(#Jh6unsI2atcpNQqIPH@1%oIQA^1Nf)f_AvOQff-!5_ z!!Lt<7+X9Nl;x}mmy7m1R&I%aos4szonOf+6=%qsLntRTYkw3UApYh_;rn&yGXfS* zt7;YUem;?3<_o-LRL!^5T`k^kM`~Dbh1?t7Pj&l6_-~Xj-}y-fTwq?;brm)k=}G(T zAFPY~BCM>cI#5dvFyKeR$Ja24$Bj`XMwERz11(my+uFM~0D(}Kht$;6R}Ige6X?`- za=I;~P!PN4&aXC|&j&#W*uG}pe|ld1hG_w~9&I1vriB`ls;9y5DL>bNGgGt+pP}cG z1egs{j7M3=_h`=H&@?7lGhhFr%03v9?;J-lR+Ho@%{HbDzjo@4$rFKt}+tMF( zFf{w+o8`~nAyJUvM!Y(7I9!c|(287TOHzmg#p?PN9vi_ce*e6Zee+EXnR)7vn$mAaPbG>LrM5RiR|!H7 z791fC9zlr>6rYuQo0I7b)ubDbimGBJwSbkV_Sj9dl9a~iE>)%umYI)h(F2pC&sx+_ z`_8P}vQQd} zE%zi%wxhTV;d*Z6DCiFAaS86+c{!e^Wo)dht&@UKkUHw>pc9-}PQWpsPuhS$)=YxT zj0~-2Q)QLKYOOZ5>_j!}jTy1Gvu6G1?b0^~W=!JO0J=FJPtW$wPQFwuZV#BNgl*IN zLX}40^3%=d$v?QE4b1$Dto$_iv{EOOVom!;<6uXc!k{t#8dGPs{?ZRm*}> z4Xt;==0ef4755pf_q*Zr$|+}(yoevd_mNe@J{=*_Dq zoZx0_J==kuZG?^XU2LkX-%GG!%yJ5Fc7OGMi58~7Fvjo@bjy~S|J}^{LqHTm?&j77&x()s1( zpFIE(vI-0~z4qBX*N;e%j<0L!he>T?=wzOmleA*m+7lw)No;PV zVcV7X!V=1WMW4pWnh*7b33c`PLNN?C!FRdfn8#_Bd0Y>og>dKafO#|CQd+*d4 z#J0dtdx?t+qC5~mF$|chX{|_a-12p2ei*Xh{u-3M0eO5i%^$XDf|u^0TeM_Q^sM`4TZhKvDVjtQ;MQ zPfNTT;}Yj!lo?ejW!(uU%K#Y^M-l88IcX;yBa#Cvcu&`2T8vw$2xZy+sA^W!z*teE z$+pO*2vj{*HvNz;-$fqk@uN#@+@^ffU1Rj_Voj>e&6IAqtjY(5GR<<`euARgTTq-u z!;zy|6^%BnO!{f#Ytr=4bM&}h)uD5a{w{iioRk6UyxrkG&DN2QTUpg z=)pgEU#^1|)w;TxK(63jZuckI_kLj2m6aVIFH)Etr9d6?L>Y(! zVobl()EZ1qIL|QY0Y=R!p4=R~-={x25Ihy)k>iA;7+Y_R$&_A&`VL6TYltT$GUl@p zmle9+g!AVd*fw2?)WNQi*WS&`&t%+O=W!& z!jbIa&Bb9Wk}#QjghpNeb~?dX{rST|7K}U$D;BmMNd4joJLZ-rW}G#U9cvh?*F{4{ z33!a=4%O^SE3LNIJN+PDf;bN_XwtvtwT;j?dkk_T_4whdqN3v0+>`HjitOIGtU|Bz z2Gn^!Ip=m+5T@qKoh~>f`#yNl_)))`sX}YkgS!J-rr7-R@%Y-iZBgA}EXBu{j+g9o zv+=MXq&uWirOC;`kszWTZ-nxn5Gm9;Q#7%@T#Ew0&%?ojF)zD92LGq6*lNK;yt`5tuYAF~1OJf--SA zRefpq8+S!0xG#WGa|`F; z*v%TAn#QAa<=K-C0gMp`(f8dN#3X}~Q&nZ<7eYetda!}E&d%qP^6H*p8?RFh+2Jpc znqH@sI-kmTGRNq(S{rJCz|Kx&$;1X(Yvy{9h+`kxBJiRrFA!F8x#ZngU2Su}KcRo0 zp+^eo1tI)u#E^GyqNRK6uBZOpUWkIzLUzBZr(`{TnL02#8YeA{t~*28Xufpo4hbBQ z_!e4I)pZPR^IwW3K;9Xu=4H`(U6?>z@<~=^auy&G5^?$=fT{E;^uf-;>W4$Wy@Be1 z)f$DUed5uQ4I`=XALL$BT6xpVE3Cti5xr!fT;%C(9|QMy()WY-h=;PJ6n}Sfs@_1B zUIlUA>_)YJvF0S~p&n+HG~f;2Hr`0p-41YE{o#L+p%|9!o0b-$W|g5AU_y^hqO7d! zdt_~CSrNH#Q^Acp8JTL7xnarzj*LiuL=Pf&KDM_l*&x!~-96uqi?e%%n>O4}SAd5Z zYJU0~M6N#c4&5q%JxGm?KJII(&0{baZH?7tx7)(m*=rr|OL{MSgvSx;YFCrZN~D}w z*#nUA2nWxaj+%zoAHXH}auJ0Z%gyUuFW^O~tLeSp5V zTK>p!bqN0Y6iO#)HitsIh@4jLI9jnATG_)UoT%28Ku9mDW|5;-{QbqTmp4h0d0D-7 z=!|{u#`-1mCmPQlwG_O~gEf0%)4ewWL`mb+&sM{xmX+IgqU5ed@kac(2YoWGTysXa z?ac@(>BNZrXZCYF0;J4D)yu+zJHbdSRM$?2=G7^mY3ACdOfPM;Yjvtm^1u3%-CT0` zv#6}0=2>Mn)R{Tr*y9pQoedePhLfi@Xi{Nk0u^quw~a+9$8Hb=2uE|3qHn+eNKzU_ z|D?0G``jq#_y*Ny0psYOkWe*LIAQCDf22nVXjJ|34)v-RA>3O!J3DJ@moFd1-U`aW za)7^xzC$B>-k;3><)jO$VK;D}j$kidj`Dxy@W`@-BhUg_Ng%pSy!;nhw;z|6mtA>+ z18h8Z@of)eKK3R>zTNH;{lO`@-+bowG2zMt2X;C>_pGeo@qqJ5VGid~jge`3gr9w( z_8ETOH`mU?QmF1H+lfY^IyFpn77fr?O`;8ZipHuJoE&&wQ4wKD zEL8bsS(9JMzi+CJp^hI;0kBn{TQ>f-PwtO1W4=h7^*b7&*kHkC{SfUq>{R9?p$*+= zwjw3edbzdRd>wIcdMRD4;f^|b6&~n8t=4RfxBik4jUh_7$ZQFJ`cCE|xM@tj>cP;0|_J?)##pK>xyHl{oCIjWaPQ!I&XegKXTEY8fZ7Kgf{G&qMw* z$Pv>+u(QHwTj^p<@3T&}_u^-5*oQxdE~u8!ItYt?al8c&8Scq%foj-5y1ip0+PisL zbq%>(vVo!0a!=KA(+)%>CBcTsd<`|9)vZSYUV~cOWB3TSG`z{aEhUzl0;}1paM3wr z0bK>A64HHOrN+19Jon*MEsf^;aNtg(5N;bWF9HXeO7Lh^!?CmPUgg9LxhU?MZ@v#V z<@47^){o@eS<}dW@$Ieu{sV(DN_~C-h_-b)h7C}%+-k4| z@qQpU#(X+YuG??x`8tsa8a?s4FW2b+HBDneh7G}utk;^aZzAaV{=D7(+3$KwUSHSR z>IU%zI!`^=IV;1K!8~rG7+W+F8ia|$GI0P5;wITAP)nKceJ6q%g)rj{Mjb-maW~`0^?sC(^7#1J#NIRkA|}A%zu7T~k23<82GlhzG)=>T-!xt& z>2POztd@Q&Dfg3Q+DXP6ek;WKVc~dGKxk23`fJ5^lEh8?b+G6yT4k5^DnSkaT{qF^p9abIY+~r6igFGtT)hdg?jBen z#xE7Fl~NqO2y$+d*BkhWO&JuX?Zbd%t;Z!zja5~h)w_ccx5-&TL(u4Oas9F-Q|j;e zU)DZxP9C5Y@KKLq*Fki~aDVVOg|Dx0oNIJpS?_9k*<5w}{(w*_I0XR5+6wQdiKCYXNtwP*-& z>)OOvH(ZSKp~D&7m_^H(tg%xcr{1l8Bw_#X1WB5x8tb~5gPI8@`w}NMhP|HCy5Iyk zCQdr3fyfCyqdh>iwt8=Eg_I@xTY9olG5;p?BW1I;TK zLI*op>tV8IfvF^4$DK9O8urrJz`$qE9+jN7Y5zsAu1rbtD|2s$kl*rVjQ0LbOH{sjgq`c;-VWGr|g>B-0`12|8I6shhj)n zNDihk7GjY7K%M5O7%4%h0hJ@`lQLX_y~itw?8vrm;azTy7q5v4a|JrYp>bwihECVD z=fe40zs_4f(Z@Cs_%sO2HSxVYEr5iIqNAmAO1p06s~ROg*tOLFxVZ{`M3cdT7zkLJO24y{c%$L z(f|1Iwz_+rv*>m|uM(jKr|79Y@zMcG(0^gV$F4tK;br}6GySF-ahXhFjo@>>2cJGI zB~&aI*qe@qO?7L-*bo8(yV_S5qwn-Nu`}_#e zuFWnH$dR4^76h{D10_5vaKHx(S`X4ynWS~2e39M9n(lW&d z!u13DJyPoF7Y_l$_3LN%ak!GIjP#Ao*9nc^fm+p6O=65yBL5rAu^~`b8oVX$GQ*Iz`)uXF=2S)Ub%t2(y9K)cMkSw43ne>QtVP{J0FTX~z| zbwCM^b!(>k`{jBYOkzbvMMg$OH(5>}sM9+6{ZBh9C(lIi(Maa9CA3e@#4o;=qv`zJ z&8Mhp@M#dkn=_7bx!&b=d*Jft)Mdl%a8@GOy8#LE-QQ;WVdb;qHYh&}$}(Ow7=7C- z%1c31?}e z_4Rt&ll8ypTshO!9PNu_6Q!=8wpuvW?6k){BAZeiquSf--=@FX+18ChEZ9bG02?}4 zOI(-s0X3)8wEkTG@_D=PxU7zZmfiYm&a(Yx1O(T1sa2{x_o;QBF&VR?QIL_97ljS? z5a%9y8X=T3z8yGh!fw@qn2oE@;l7G$E995__QfuT!&&R5KOh_7OI;sly*8KQp8hrC zDKPV~i;IhVkzb&a{5$=DsVVJpCPtafF~rG2hXY1ZT}D1R3uuIhd|bi?it-cMhHp8}R7&*@oD8VLZLk>{Y_pg8+O+O}YSC(ZY;^W%m8esVy%Ql!d zpVDmm%~-LgWI~dn6w*64a#jt?ZIybh6Gbg_ZS33z%{3XZLa;m;sHST+R?u;-Rs}?o zph;R)bwNl|+-#`TL3=O1n(pYGb+{WItSnzx`6sP~n_y>XDG!)icX|Ps=G=U-f>qqM z;?vX9e~9~?{#3ek6EhzEMaZj;Yt;=RvF;n{f0^4}@EZ8xueZD1f^t2@MP+u@+4=eX z>wB_}x0{0j#Kp?ek}D`oG&VL0=T9#WPrqJv`Pkco>uf)OypWqA&Kfs~kV8NyLJ;=T zR4_;_rLw~F>7wnD@XHsiW=|;7+lgM0OHlbfp047(%kI7V0+g5<%FF1U1>FS~e_!{t z0#x$xf(bcqtq3veGRvlMGz-K~#-h&z5xwLp0rZ|V%M)s8jcE?BEmCkRu}!uBnn;@nI{&l zE+;eMe+F2zPbAZoWg(c=RC+QBVji!l@_pU!Eps9+Fol*Mf)i)4eD*B~)e<0)Y@(I)9 z>F5I#HU6SG>Mn@RCJy3H7qdjfHRIGMw-Qyf{a!Y`4go~oPs9BYr`=VIyVK(~Zv%_l zGmf72j*ejL6UOy}ZQMAq78gLi_~Z!@4mK3WYg@kd*v9NYb+fg_U zRAvQ(6`oTVQbo_^y0S*FML|09rxu$^2B&CMZ?j&FdUIiRa8Fw+hIBvN?E!-s!VIrT z`Yh>n0q=$GOxfyey~bmelXcuE=ef4i6yVJFLOQmXMRpVn%(TJs&eMkNq*6*VauF@R z{OH_mG`^$F@lJO4^8F+b)+9+ zO^SxH&O~UPe_7=JN9V`g&$_ECL+Q7MK-?0_^y&P828%8Gp6mxVWeeIzO$hV*8=X z6e~2}?L^R9+t}!I*uQ7GZ1@TPHPF$aeYxoKzPPCD^|7tDna)c@aKVo+J$Og#*fVy^ zCb26nA5WMi#UNu~Oydz&1*G8r1sG{IVZP*xmyd;tzoK!1eEyjc=_=|DjT>ut;|MqumG zp1T!T$nw^vlQp>R+|0)d^v5TQ9;*hb9V`_KG0sO+6O9xug?}l1sV1Knwz}fH{k`0M zKUMXH+g*HcwV}u}E$N_5Hs?oTe0_d??*0lC0O&wedpRQ>jrkVW(=;=OI~^+f+anb! zkKJYVhYuVG%8fJk^!b}Asnh{Eu5D}5$qb4oyTIPTHkU(q3j)2l^FdP}vd8zz&;gw zUIF=mo#+r_#~q$G1htNqR-5~7tpRh(ML@}>t9vwzNLW@=KL}*NoX+q4aIvXx$C2J6 z%{MEVG^YSburn~|*XguB{`B-zAg#v1!I6XX8)lNs3sD}Z;y`D}b^fg|2V68Yt%GB_ zn3hQDO&SVNhhB@QBr&PjSuONwo~6;s<8O*m&$Z{MlDbsVjhi<7jzvz?a6oWtQz)-d z|7GvHsm0wId5mXOsFYnnGso;yP+|tJ5_9P2`fSs$0{n60HFMAvYdC`>RHE|hZx>zY z;jJ;`t!{%f!Q8d7Qoy zICZq^}vT_S(sb?T@%PNBrAiR*mjV)x=* z4MRG8?8a2?0Gqjc{9C3`jDxI%bg!3Bx>i-vOQx@~fjeS|m{Bb{{_tWuuqEv)49AYJ z70Y};Kv9T{_(1D-#9-zNCtcjmZ}^rylUQugin}nj4`le~HkQ)m0(lO7F>2&3dxl`< zQRiX?i|y$(7vCj>lY@pQ!}7NqehH1W9(a_C=4l`r&LI1 zP7_BZe64v7cWI+sao0a3Bn+M!++2a9(C@2HN7(V2mApJBr#yphdx~2?f~k;{p5LpB zGasAa3kc=c;@urb2HQ3Fr1C>pM!+}p-M}7wKR-7}oglxLZ6Y8G^#(P+RB|kdYrvQ# zfCHid0Ffb)s~a0lnHZU?9k!r>T6F#Ra`SL8BQLnNvJ&80S&j@o^Oyk3GtuWOTb~yNYDU{%nY~{W+tB<*v4oZEtcWKxg9a)mQ68_Kar|UY zF%wtX0`e0z0~|B5Wi8$)D-&rYBJ|FMmZTptXbx!?Uw)kaBXoX%0(%6T898h3_)6bPZ{gCr z$%>Fq^%)`d^^aFyL3b62ECjN*yL-yM&SvgPdU~JlyOrMSFz|EhdR_wpl!29%*YDZx z{S=?m7A!hdPA*T!YU%jVxE+|eP(JZBzYYxo(zQ47jTIUqj=_fY?ZCnQE<%kfA|_(42h( z-h8sBZm3g+wFwzjg1HepQ-&O?wPU1g#XX8yx00@PF-}cCI84YOo@U338%U&SuxGmF zDaH_|=<~M@x-A3Y!%8h)=d5XVok!XuQ<)782t8Z^PFKA3EO!YPM=oFr4wi*md=Z~g0bE2*$wCtgE zT=eORYQ%`UT%>WRteRrKxL7p(vgUbxVvohQ71am}aE$XcTQ$Nrw1rX0@T&UXvU(Yg zlI{s9u`)3ncMXU6wNb(jv}U^?Ci2z$WOGxWB^5j!>I|OkVK-S1TIvP3+kUy`w&8PQ z4|CCrzzF7&nunZ0no|l87$_mHzy@aKc7D0HNAXduvT+G{`cnyGCLK&JLeq0b-(Rtp zf7Ku?mw)_ZaBn)A7o{O1?;r*cx*s-GY~GG~R9UZ;sDNBY4D zsHF(@2&umm6{u8g5O4`gkD_2B+J(R?p{4l3W6i$iO%}B>B}%eJt5`86+2OLOXur|u zI3>3+G!57w8>wfT(B`VMx41bG#1%Tmuv*xkH6cn-!bHkBA&LJSIGMo8{S}lx7zVEL zr%98(rr}{Jm$iujcb-mn{f9cX%rGrS014PxdK zk7(*TJo;qHr-b2Pz_rAwW)7G%RDnk-*hsQOA z_qzL;xseehPActw?ChiNsA>QBc%D|1;CC-zyhU0Xlc4FYXRT>LqO@5$bpx0>z!O#9 z+S&zd8Fv#3bMAb1*42>oqc(`YB9^O4Og8!-7Crbk7zKOTa55A8T0APeqopbG;OqJ( z;u5998eZN*roDwjs(rKER}OEen9x+j9r9l_sly)lR2e|Za3~g~QK6&c=UZ{^m|Qs3ymd`YFgNZ_PUv!g#VkHPJ~1(oHre}S z|Iqn}$r;NVLfU2B@4?>842Ho#tPF9Hk)V1jdBDJu4Qz(-(K7VDmtM>VM59e&GA)t4 zXqx<}zDE?7q3Rl+_mMGH1~)%U)NRo?ndD};yrQB`KX-muENV|eS87=jrk-3_9&}x9 zL5a9ApQ(l|Jbkt26j|o2klqF+M*i5sMNOYtAl6m7KIB;&L6>0#IY+Y?$0U7plUr0z zMrund(NX4uDI0gz#_%1V7(tDd%Gr9^C8lX4it=;S#em4mq*M#hc;!sY!f}ndxoA za_J-2aWQ16dn2)7XFKY#m7fwk@C*o;BgiR~?-kaAetpdA#%B}WK(3Sb5srrZXXoug z{dvA2EF9-7{cSA&1xd+Y{Op&GMKL|yM^-rf(@ItTfwB)u6do%VsN%X2)IES7x^Rq!Gm;Q;xz&ymkOWkkr zW{XBSh4?rWuzu+Q1Zwdud#sNI(bjs$WFWsBeQk~+Xzqt$kCL#&8LhCnV)jcO``z(L zIYn*}Cs30kdVZop=Sf zRs>g9Ha1}Hyqujs%woSO3Y8Z=I>bNEJ%3}B+q-{Lmj|w2(#aSjmIbx7--R2N+&IZK z=+y~56ja3p^fB9eEy;CC&BpfnLdgRsp<^GWE}-c%xjz#+Et+*E!+laTvBh`$@$^%~ ze87pYRtV}>N_JLFhd-v2Kod8cN{W_QA-dJqijo!s+$GYOVX5E^b(P#4yj9YRiYwi* zhSDvtSa{9e_g!<8Q>y+7xXY^0&f0={H-6WGXs^+`YvbjQtondgXa~l%Azt`7=n&!2 zWmiBXR(VUy2EOVyhekaSn4Oz!->~ZVTT3v1t`(`?16GUqjPP+jo*(*Hse_M_8`pky zp3Df_7Ysi9tV}INvgZQzhnU%aX2mY^V%@auP}QYU6(K8FlS5v97%YlAgoJ1@IsIe| z^ziZQtgNU(qh`;^`_Nc`WuK&8fEk8RNFyOaZau%ghscK*Rh=~Ew#KWkTheRfr|4Ck z(zSw`YijH%Fd>)6=t$S6l*hw52tv<+_i?p87oB1eZoCGh2`7-7u!dNj0IO&D=uaK{~)WZ7Oa0MRi1s znPFs6xTI26Ce z6zRx?j^EUqdwm$~@kRbYlvBlW(D(Cf;3lYpgsH813wwMu665ww=%}Xoie{+8%5)~G zVg{oIi{git4i7^a_reCFi6Hy=d3ggVA)gDZI|6&a9#8D;;<;;Q!tfp^yIW4a({WY*FwNjk(FAb(nL6MDm1csvl>jjUUSUFWL_n_c6FF0A@d^A%V@$v}G9T5ZX$ z%FOcCR3juP%d3{l^{%LNk?^AO-ORAS?$mA@>H(Q$;smbof4-~5oRsHFVB8Dwac|MJo`D%A@Y4~UI)QQ)%@HaCn8!)vXd~oh`V`&(DRqfPp zDRH(>e8LMRU%{(C6Mm^uR#V_(T7Ub>SG)^bf4|(I7l)!byS3*?GGTmoP+9*vTI-qZ z9NCpr*{GfVx?5Ip+(I*RLAI}Z(HjLm`m(TU%Gdtus@&Cx1$C?A&aCp~6O z8zHRSz@gAMGe(SOAaED??(QPM-T`(t87`U?>Y1(fX_?|;IUgyPoczhpQ!>7oaU{J{ zeJ@Z^yjRq_3JaYIF2&e}oomc&2^x<1dmoN)woD*+aD4EIDYkfgWt2$(j~Oj#;MH44 z??RKr4?fKEhjFay(%@0o->_zH*&CugH(iS~w({#ATSHrCY{mD!YwEDG(8R4eAXl7f z;Y7bi`S(RA6dYu#m9V1AelNS-`x-PZiwNJ}eT$x8gMMgYGx+<1Kv+KK4zom(R^ zY-rG4`(g&%_)0Oa(S_xSe>lQKGIptZe@G4Y;vydXpw{H@*5!Y(fD680_3Z{BEpWb4 z+_OpJDY#WVC$=}Xy;%VL=l85|tE zXsN9=%ndh9Dmn~$aFAVI!f5-+R*O!J&|fQ}N=Qmy>Qe3U?7ym%YF8IfnLw@;9q(Y} z_*FF08mEFXgYU3`Z>AMJ0LAh?P8PAch1?jA(82>DZc1+NXOWqr7X)_rz!b&PSgYgN z=}K&vlV5D%{OZW%UU#brlRX4^=T>a&9cZZLbM7dA#aQ#|lH{BbzJ{&1f5~{#TCNmH z68(;;eODY31~WE7zm0=hX>odEEH;#8f&qKLe}yA_WyN*n6W;@4*(l5ykK43nJp?C_0`!0L@Ti=}3%xo3y zAv_<0G<6Jt+p}|g8h=Rb$_-aZJulKx1G>yYGMZYj!4COov>@}@^QuyEA@Lo=HDc+o zcCjx0Mli?`;bEgJy8qHK#kt7j2Z*cIDHjxDDsXCWLq^PQB3TWKGjGtTT8?GLOZX&j z4aaw)3)1u~>kwRL8uXOD?7=Jj2fI_C%A$|SeP~fz!SLNx!3AM)?OSv3^7BItTn^yd zSzB9or{6pCWXgCKZqVWJ>vekL4(rcvu#(|HwIDea8(`(e7pt-Sh$b6a1*4#>E#+A; zwlbh3GLBdkaEEAN|DJK}Z!djtXAC2(Yl0`Kh4~dhsWVMs!|9s|g>nS}S3Y(r=eH6got;-xshT%Tm5)Rl+9GL;v!+w7Par5xfi zn~3@MamcQGR17pn51zIUaHgZeL5|CSJwga;2fVz3cH|5XJ<6&v_&?{D!D59TbHr&nLjbL}?A zTY$LJD3VSjBFvOAWp#u+1I``m+BMgHueEEC;F{N%MDWboE#Dd#Fv|cNnkAnU zCz}yNYxbWs<$@i_wY-cR+tj+EmSxtKx-#lb^3mvc?yKEgx`S0fsYVs0CkO5uXgoaJ;)i$Ufh9qr?#&;1#HE#|@vsIlhC%y< zb~+x=ub`^Z(cBJa>re!0KTutc3P|jO=@-&I)c%VoVXM z6)If&Ee@-hs3QO&h{yhBUvtb`4 z)1VTdQO=6(Q?%O%MZNOd%jAbmo^bX5PuIcd($^0oA6H4r7%?dm8{RJa%q;UWN(;c$ z%Z)(SSGywspGWv(OcY+523pMo>Eaf!_XPHI8_b&LGGO*_U`ob(E>~Za`KcFg9GtQ! zGKj$5{5{c_BDC`CbBoxAq+!eBPdy}bibr3eFxdsUOYBZ{m8Ra(L>A{Yr96MLn#cBD zM(V;BZmZ)*VtP^+jc!OxN`A6g;#i6^UnGE^slR)Ez1+dT>IQan`NKOZ+f-2voT!31 z=8*C4t|E0q3mqjKlyJF6DID8)f?ENAk~LAtL96A z9OJ!u?EKszpxn^f>Up{h#L}>bbY?<5$v`w|fEyFeXATq@Md1A-zzi;K=$C6IM6IfXZ|X|zv(|?fGJ{iy zPG_*++V@qAhE1dt8TV)LhSKp&hW=1sUP*RzRtmz3rf5wxP-$SHaF6^ZpSOHMGoQ$& zE$3Ml>#B{n_e$M4Q?u`*@;p{!t`YA;h&F3Tl0AVg^Eje+e) z;i04BMW(eYdvvV%LJAYQK6mNuW3T({cwCDU`;~GV`|8(qXCbJRfnO{FC^qBTvo*WU z;)xp?B&FQsc?=zctU+SeYO(X0+K2`yq3u4evW3+uZgn#C8&9v{t4i)Hc`@>lGqRqY zKea3V!Np`mTDxkujdLB?UFhNFr3Rz}=SZPIxS@IBPPQSq()YaAX=wG+dFlpKsRyJy8PB$>0ZMQ;}K9yh?QHY=*FYj z8k3?vm%`{LKoLnWZS4=KcJxg|4)HxKFGmJVTXXa+ZgwKVNET}41dCX^HhV%ES8*pK z6O_$^bE9OG@g!E8aML-OUUX+FjvC4^Z>ZytlNdjl z(6+JHSK{%|6cE~Xy@aChA zq`ANM!aX0^G$y(SX>H z)^*7-Mkyaww_1pwmY_r28t&Z7wsosY7ZL~B&gS>lk`Y_NrG2SZHIZN+nT#&m19hv` zPxu76d4r79=@kxx!m$l@0o(^1oI{)&ud*^?{%pO&i-W)aU?Rxvw@a{0Rm%wB>JwFY zS3kcF94@RxCZEre2~Jmz*KMvd_Z@1ow;_`U_W^P*x-A0wx)&auC3@EY9q*z0 zJD~M?znPH-+-hb)E9>iT58KhdBsU%gI4iYVAe!_c@^kom)rw)xGAD|JvNU!{L9{h9 zw!?195z?*ZS;K_Z2Q^WiNXCrki>5(vXo)IP-f?7%XsZtlT9ltF;^^eHtq}JMOPAhxBjvy{+qMmAxrQe9iAN;RV*Gh$73wd4{vtb_Zaw3rIgVa#+AoD6a~IXD10 zMWuEt;>hiXsS)1#?CDe2!H1uG!46lPfNhs0qKRE;rFH~cpgy453o z565#w)P(NB?tqLDzILUgm+hm~Iinq$&Tc|x=YbXC0({d}gXFG+`9wxz|h z^exQ~Aw>L1mpc#+B-XU`y8nzT;>`zRRDqY(hNJyxo&&hfshHz5_+A8d1d_Uc0npv4<>lq%t{3UQ3WmF;t`4v2cTfnC06;VX0)<2HU{PYe z3wY#P9013JIhLg`14sv2&G7^QNjiljeVAi0XdPP`^v@-BGjn7KiuugsPF@7*G-g-m zL)E_>HP^-BF-N>&Q(B5&O~)W4`NJ)$x7&_}xiK$bu=sOqB!BhuWc_~h`|QJ@!HO*` zgRDE8b-(o8%BkQ46+CRA_e<{aGh$6Np2)qiRcpNzTFl=vNl%w z9O;VFgx~xFRqPBrX!Cz|aIjlB^?hiL@JRRg9%Cuz)v-Q5kEO7&>KPC2IlsQX4v2+N zk^$$~uP{IekbU98gww6k;@QHBJMeQ0dD^h}HE>jfOIYeq`Vr=#WW|w5}N+6`91SO_EeuYygW_$=!j4pApScDGZNPBJV)zfj6 z{66_dP2z4L(@$q7x~)xex{6UMh*{%Y34&Bm82H2LX+=9@&D!;OQB#u=u9bc^e2zo%$`34F-hc+4ETZ2$;? zhTFukid$XEbZjN6J*}vyWnb@{J0=z!)Zr&_E>RxM`8C^Do_gaAU8t{sZy>6t_2*Ow zgrQbG#xk#>9(RlHk6d;(IvK7%&udI92E;TMs;Kk~S;AR^6yQm$mU+aC3$Z5@Z-_HU zv6Qx64gZ3*G{i|F@w_R=SxD+xj;nNT!sy5qNOh~?c|yYhOi#ZwZweMx9`I;{dHofR z*z;teCI3Yv?vSI`0R^w%`?Vn8|8IZT;!(&1{nBMXDhrz}9qL4NNzaxNZvqQ@@oSkA*l<%Z@n%iR7kv$3b`gf8O~o7X+liI zBD;#y^TQ4oi#8@B+>$9#$mkD{lxYlt)>M=wO716ND=&R7ZXV{`?GBiFej2>D%d=eJ*qFVFb9L7;fC%?$`TZngm*$ z-rrtF)T&;t)GE8~3e*CaUY7h`&1W%V#yK!+@n|6dEa1wc2{%5nc?zHlcoJ4Bph>ODnT%$=m#96HK%$@SHj!?l{(h*4_S(n?8lLd&v~Gyy}jXK zJPh~C-DLffA>&n5tt+->9a z^89uEoRBEf*4A1SQh%3#$m><`KCKI~(1IxiD;ks8RZaENrel0>Xv~N?d*r}UEM;<| zRFC*pSp(sj8cb7|sqQm<(dVCP^{9VX;lGJX*$qM;NlP)5bs~j!PT$ea+gx23)%NUV zpn;{Eclkeg(Wg0wTKJO}S6XW2Uuwm4-R%DBeKdj|g#xLD9_lM7CM(S2Bu#s7N>4jD zqrLx>g{Le+e;r?1(y*ul_5ivAfcfO*<<)x}R?`JE!Z~fJmvZTP?@tTwV_lD&f{#P; zo0Wid3;~BRXkp9#i?N2y58eVnCG4$;m~+ijLE2yCwo_|7+A{28Gaq%hiDy%aP}emP zRd-KAStNaQB=WJd-4YKOabI(jo2hr4LM6sK4w(c{C$Lk6P1dK@#S-|Pmg#ev$GV|> zcsAx->P_#RpT;wJF-Vd2FwRHHx8l<09`R-<$NGn~*S}OdOTT7hGB{b@)?K2M57EhC>u>7q^m-WI5tWN8dAuu(O2e>fU4!tiAHCpXGMIJ*m}W|+ z^UsKMuv89Bg2Y6dFesl8pCO3{5}xn3qocFDY!QEWczNODV0sBM*y+v|ewcsiipPi-KO!5x(u?ua9jiGooMMtJPPVPr5JGsu$s3SO?zw2YIgYpQL z#o(hZ#);7)+8&lX*GqHrE6gGLll1L#e5Vw7yT&O{pd@hvbp-H`D6UhRf?Zo^wdaR2 zIYY-c`^<39Zd>z&{h0ndt+6x(+7jU>Jc=8PXuxqU_SidXe%fCf-yKN?Qc?)j;rt$x z{Q&f>LAOh^&fAmE7jSBi?Nj+7mI`=>4E`M)?|mVMq4R*GfIQ5G3t1V z`5?B1HvcO8sXs7&KN#01I5%by%>fj> zvOqip^SSx%7n*G8r*#nMb4=XhYv9nV-$VR8 zkY1>&`cmir+N;9Veeo695*U2Io<6W09vr|T&(F{Q1pD$lJ>0=s^T-#yI49;9zWY<` zmbkSdk#gJq4Vnx+R@*X@7}ryCdOJUkLR1cKDB2#UsXSiIIku0hZ*`1%kWS)myp@n> zcSSu#I}J8$0SU?*>tIfW=zTP0W@hHilW4DI1HV@Veitd5DKt8s=aCTNhN{6?cHwLqiH9 z!+}ck-7*iHb#`?S6aR-HSvT_b*W|`wuu+B$%#q0almjZ(ohS5_qIH~>5)g|)UFK+c zIM#(D`|xfLFQXhoO7NPm7Cy~C00>`M%=w@q`-LO6FnKmLhP=(czFwCf zWq(i#K92H|H%RE(pn&A_op59%y@#=s0Rq1`$@1ZTQM`lQBuw0X(1z|t3xsKtAYLWJ z`KfDbAo%3AZIv5vv3y*UXv|Af4#b-6S`<%8REld_mjOxJ3D^LWb-ixipSt{r&N{p= zr^~83pZc-&p0MAy^t4yky@7=ez?d0yTAe*T5uKe~T%6zEe6sPEJP=GyjQ)U5(&gc; z|I8zt(q(dHeaZd#Dq?^U5B+SU1%1ikhOrJGnZml7bIES@8I@&V`EE3+_7;nR49S%Q zB7?Y_sw+)uv*4$mG(~}CKqCev(sFJH+vIq2n3R{==CC#Ix=_K7Mk34b&owXajx)jH z`0D@KOF77d;r*DNYN)0eAV!Q->&sz->8h^ijVmQny(Hfd*0$wAAWCOna z#M_2&Y{oO9Pu)7NJ$R#ZqkRJd1LihBCgM1J_OByr9uGj8Z|mb|25iVCT$);1&rb_o zZx^6GP&e(nLf6ENRzgTfNVgpj@$wi*^s-6xn&)?e@>bM!KDTXq{x^xJsgdLDQSg0V z$RF^h1sysgUh9q)PDb?Ppwuz4t`2mh&@8DapE%VRvL@La%0wA9G^ogJ%N2dWf>$Uv zVjZ5L9b9@3Sh;9NuPID-d_un$Yu+7FYl#+>b;(udlWW*o=D=zUi~Edgmeu@X3EKGZ zujNUSZd!c%nZZkhgKY8 z?RuH7dSCvCgFK19IUp29VP+;&;7<+i05L5+!OzbxF3Z^d1arC&?lk^In1h{iN4(X1 zn*B(R4LLGlT|Y_fOF~J4MP!72bokdQGA4b!e(cXxNVgt2(In#$0-e@p0L;`@Gy z%6IUJBKX!P_|oU*cZII^x%&8#fZ|PB?+K02x$Z^ZZNh19%3O1_>oVQ%91sKA?_aK4 z^BwMHt^u~ePJ1ICpI4%{S3mp5tsr0n=<74wpAuD)W3;Z2r7S8)4>Fd{|L&=?5K?kC zcJ6*<)@#2ruPmBoP)MTA^3~SqVO%;*CR3D(k)U98)=}@0FNs{-uxzYc!QbNR5EE}Q zYlHDo`m(@#)C*c%8*4$fCK1Xiij~Ie>R!+BVh&MV@}CiP{5JFzoH|||^;Oh=v?O}4 z^_|{>obJ;o*kSQkrx_`fEpNlhWpPU6_nua>xhZl*fSj{05tCR>Mu#U8Sz!ZY|JCeo zTc9?r10q*)h5^;dx&y|X$n0)w_*28d;mC7bhB2S0K8F~t1& z0lK5FEX&?mkQDTXC1qds(M-NaL|o_M^q$qK(iOSUg~b~rUPl<9IJBEyn#r_p=&I-5VT3j&&Ng1O4g1~* zxlboe-fw<~LbL?oAstnLr5KtOn*8=b=})si{*kJ%!uf)NlOIIjR?+>LWX zO^qognQ760Hm(lKy0JaU_FTLl`uyohl&A5S`WA;$X$Hp+Z1|!vsOdW$6yM6l%L`q; zruSPT!ee$Z9NV3Cb2CHyp+wkja5+(KS|LJ&eg(mPJz3s^W?Fgs6VjN5akq0ZYnR#m zlJLt7z=a|^mM)G4p5CwD-+GK$p2s#`yns{=$fV~nySMuZez)!Hx0&~C!Pi5-H@!E| zyEh9j4=?|jYwhI{oQzMF3j*is-opDC@5Vc*B3j_3cZ4xY721B`Vdnx^SnkhPTiwn- zEg?tL^}?*C$p=6Ko(+<+&hvbGLpJNKwBfj1ozHGf`LS9N4r`}Kp-@U29c6a5-YE_@ zrR=+_(p}X9OojDuQnt<{ccEd!)k+xODhJiDUbp zyL9>_t6dwF0nI)`_HZ+-c$D}a8gvvRcxmYfL&aHNE|c!1KsBDl z1O*=jNeoI1@&T08WFcLIV3DBnCgo8 zJfAj|U<1)eKMa8`a1Q9|96B7f2mb1k-_Odro>rYE2#E;0cfPgeO;y7^F z-hM8JR~xrz7I@r=M_KoQu~gU78&rLJKk0Z(B5U$sgcTF3Y*2GiIVaIF4ks~@!l1Uo zeU74A5@?)w$l9(MzlB_k1{Ga&Ihn3^@0%xCdF^R7l0}nC&nNOFNjjLtcPwNjCVEMH z*wX_0U^rA>s#|P}maREd4Eq7%!Cz?ezJl58Jm~XBO*G+8)jUB}^{w+#m*5`@60sDE zCI22``UoZ|CakPXc__&s&v@KtG9iDo^7%p*4cPtf z^;b&px`n+p51Ajqvp^rdW(dH%@lkxk+41PT%*B0zD0hTJHE0mNyZMgf8h}~EOjg;t zlcgMWY5C_M9fWqj-fbk1L{aZZWAi|=h6v3%{g%7nnCk(>so5<`FfZ|E_qTX?i18u? zqO%ER_B3^7>fH3@O+qhMPc1hG2mb2lrEDc{v>&JrF1)Db@h8M*|G$ z`dk1u?s5NmpL4<4^*EN$8gI!7%E6l3#tArhyvDZkcJ^{}dw0rSY5ppukFx||N_Kwt zZ5ywxwA%Gt!usaHl=* zQoYuUEBa?tN|5D}zX+?zS*GU?+F| zcsSTkXO5y8@`{S}W~La%WsXFelZfe%NWc0K?LgmcHBv8TD+gjq5) zOtw$9WJGJl84sM{w~5C_g_KQ@KVUxhjwlx-T~mEjAkY{_44Gw(nZR%^s!Wm8lU@5E z+9JtrC8wH|Z6cr`S%ND_zv7s-U)peul%=Ex`Bw0&RRoF~62n1%2>~#t;4CJ$4Abf=NC8fki8bsftFsLR$Klo#zg6wCifbQZJ zHeI-vs}85Sf9W%9-o;v*qFRfl1TV2xGRLs2+vcfx+^p3-_v5HeF!HliY#&1sgZ?K3 ze;qb0oP_qG;vhbZeaRnE=~vJqdl0;8$mlc15f=?^eCF)fmSgk1SMWl5qf1&=GFxor zoO5KAO_RDhp~RB?$6cQLYIYs>f-iUPux31Kx`-*vrTtQflrzfE$(7nZHG=B8ny+1N z6J3wtT@T^X*o>z{`mkkYSuM-9oObISEgfAQi{`S0@e<0Snb((7El&GehhX;SFm_13 zk0W|#r)x`#i(GyNNT)lHsRN|o6%e5UtC%9A6NOA-O;gc`1VSisA!Kdn6> z80S$}^A*dJmyA$?Z{HPJx{7HrO4h(wWHsGOhEfqrMDEjt{MUPm7kAaNwh3l+H+Rlz z^bb!ykz{t`)&1tK`V1Za%VjuPe_x)8=Q%Go()r_!X9wUR?sz&X`)e8o+_3FkUiHv=L3GwpsBA6}h@L%54BJu`nYSK)R3l*ni=;M}hIudgl4&bzz%SNBS zz?CldW?)*nir05cgY_Ymk(1$)nb<7}x93c{<05N>bW(S-PNloX!g8%Xk=%c%7cg{f zr!hP6u7Af~pkrAs~1m~g(=X6pE(G?TL}89 zFgL)+=kuG!5Vrm}xf*jILXaa^J(dyC%|0JEj<^pVnG(%fU?M;0I~pL)mz(2nMS`TvC+rrhvI&A!+tPE#zT zj{$+OT2@w8r>^NPz1o!84W8CqDRMPSiln6r$9@+ueqdl#x`P;E26f0y8N6=DIVY?W ze30^wXKq~xZWY-p{yc&&7kfuXM-zT;*J^q`x3qe%W0&r9kz*Y7p!o_dy{GA9z?Io~ zTVdCrNndPZ@C$0QW#v@pdh_Kko#tkX@Le5js)=I(3kxgG{X>^y%B*EW5Knq1zDlFy zTvqk)_W#BOz z$WxhwtQa%8>T7Eu=)W7$uGtgq$I)(4ziTkiUG<_;%4qJc{-F*@bUk9YWCrSzG0hjhpmF@y|YQZP|QZl`+NEtIEf{^v|p;4tzTgibA zDNh6&41b-+x7wK{j@?9Nm7A{tLoUO9&o7MHFK9L|lvU|B*9H`>8hSc2GFvLopwi`h z`uWSY;M?}4gCLnD8=eB1CP(V;?y_Sb$G*kU1h4^ZI+V@ne}-#`t$QKQm!NR^zynnq zv!1E^SfY~Q7z7D&-(2A_D z-7wp*j9zeret`E)YR(pVI}@uFY8Bq8?L~=g-5;jNz~f!(o;rvD18*-)VuhobovE3g zGi88mGeO)$LSyMe_iScnrd$yurUIX7Pb3r$;yYN}lJz$Z6XumOO@7O=xmJ5nFHqLO z^ub&>?KXnS8Z;qus42Ep;Auh(89N_Hy0_Cg-@wPgcAnz}ALIX~wkh;UGj@E~y!e|O zc>Z>F4xgtbARqv(fTRXG92pq_ZcZ&66M`#rc{tga90FreSZ~&x6?i?Zt9L=EDdC=?lu$z{M78DAS`;~#^c2-X}(K;O8xR863 zl$po}cK4sj^Y4}*HdFpunTsPbuiljZC($H@+3eW+Nyi180qbrzaWQyE_QFb7AJ^ar zKT@y2gX(S3{M!i%U)OHp$6Wi+1`i2ztzctscIvhM#ev2obXZcX?c?%IIzG)@Mp}Z| zRZ1TA_&Z&Auq6A!8E}0HkqT!FMGTq4JF=;%>Me^f#VRHR^k6RArj^leVKtFBFd$q0 z)B6yhc;RHwNm2`=LbUt(fl-~UXSQ()z8rMDoo+-(zx$YUl+7gjt(=(e`!`!iW9_L_z{yy!xa{+*6b;O~_2IKg1cS3n>c z5da~C97y)8>Xt;Z0WCR<%}pp|A%vcD@@Z zD&&l@-;bBF;gm1Cpe8 zxZcu3Bs$&fGmZ`hcUy#!Ujhpa*YP>BL5Hp zLQ{qyzI%DR2H+44P0go$zqfs_`!jG&Xy^NE04{MpoCY}YH>754dv?ApAbr9EXi|*w z1Aw`KhMR|H>t!NS4o3Dgp1D!4U|gNbU|LM8QC-Q{Acv50Fzjc3y!yyEID={y@94Kq z1Vv})^dNq$sNf{bUTwiIR;0*3`}_5oaFCx24L+OLFjXUQ)d8IWsm7%_y%xYZymzIkJ&Y0iVSRaLyY2v_lX0rvI5?xOm=i~sw4A2XeaYaa%# zZ4Ict{d5^smS}M@M?SzT$PshWCfC8)RCRv>(_yKi#Y&Z6DBFN~m*_j8@iI#lVs%;_ z$nM4(u%r8>48eLHrg$79nZFeT4a4UDZ}vFKLK7WACo}f@GfU)8pzsf42QrKtilL?VLa7Cg=(sYr@ z`XLCnzJtp|Q7&!_=bXc|XWFN2|Ff11XG;5k7%#r?2F~nJjSW`V8QMJGE+PwwFX zEslFMNOb#zOq`!GGE0`pQoT7c$NbnI$Q^)QlE+00KDxR9V2dq%m=^^a??r`VEb=4k zGueIJpPd6kPTQL)uEUl4OLVI0VT&t=V#M^$SiE$B_y79~s)>R5iU$XGk&zrKoa}c4`^sru^r6RUyKO64HEJAyA0s%-UqSroLcc8dsS@(+We* zk>||3==h$i=sqH+M)J4Wzhki0JUId;7Wiqo!vSnum!sWq| za~(dsy(K99snux*-jQz?YZm!EfJ7v*IrbwubyP(9Kf(H|Wx3;*4(X5|5? z@|91mcSGPEuHY5}WWLJ>-}OId{~4$6DkSkR*1m~RQ*On@uIhGHbG?pF7@Jiea($SA zYBB3^Ds(J-l?Q7$>DiHf(ENS4NG;q z3;zWa>d_?uEiD@3z9{vzsRcm|d0tCI53~;+2(uDCDV*0PTj2btox>CN#45j=*f=wW z|M@nh2Era({~2x=O(bl{Xw_6ab8Zfg3|cen6L)b3;}mTwQlz#C5v41fIDaHlq|}mZ zC5;rIEet1Tlp-=GF4;qJgr7&*7p#F{#%zpb-M@ zi4ArF2}t2LtauZvv@RDo&YcO-yK@XJtmAl8Z(gVWde)Q6Rg_D!#?G7V9!RTo=QYHB zJZY&9Pf{Oq{Vpgd$y%t=>P(a`VLkExRA5faNX0fCE6G+ZWya9yrhTq4A|S3Wh@$aA zEU${sTujA>9*38+xwQrCKaik#5Y;gTYaLM#G?d?&OC=WVf(lrw*vJnW|Ft zr0~*H2|AD~W3^HM%*I26jJAmSwe*p=ZVBq!#|}L43T|@;BU9~SFeNaKh)}fymAPNP ze*Nc^JhFm*4L)p;-!OyX*JDy#xnOfnu${~-B0%OQR<6pQ( zHUbTn)GAYouu8=KxB(hZ(^wD0AAkIi+7!|+8S%aqCg=t*2>=CgfN*eU0SE{^jjQ4{ zw5CaA>=PISP1ppfZIv+RoVd+`WO*@3C!9-CsaS^G!frHV!(2yvXsg%krH4^4&&kH} zW`SNo>RR~yNVH#7;(ih!E6>7VymN>pHFT0M6R&-r0JnPBnufI=~p@XRahTNh>}(l8 z8hSbFeS4ftXY9S3m$~4GLSJplT7{BzGQd@h9aY7rtxQF9KZuevhYe3&Dtq!YIn83r z*s)%V9k?+q6X^%Oh5!E_&+C;X;$CbkXp0>fj_P5@Ec9%cjk+Y(YYzZ{6o&i{9uT0L zKZRSYiJXQ{UrNbu*|m7e|x+d;T2()Jt}hCrc*5r%ynNiwN_A zR91W9nlp|hh9CAQJsqea?R2(xapNT#%+#+Rl?vRH9Qfx|+V;%xEciAQT#l*EW;MhqsV#YK9W2C7@HG{IT1s0H@w*+Ns%gDe3+fTMh{Qw z)0D+s8oRp{+_F!{RP4V1%6HaTflib;f6nn20o2Nu8W%g5(A%!Y@h<0i;%V;?8Zo`g zAe!Ma|6tIs{pLqcCK?&cqhER{VHdLZ`K@a4B27;vt)t1nAxA@=@;|r26Q#s812qG7 za8Sk=3D&*H#L{tEWA!p=DVHM&wQfRmLFhZk3$2T7`Ig+*ExT^(pITkZtT)A3Gpgvw z2qjYa$&{l>Yk5uIhnx7N(fng3Ju#kR1 zoa5>-?sU6Ca8#RiE%A_VZ(uS|tBXGksFUl4bENl8?oo$jQ2rst2LAUlKJf4kJ@?f| z`cJ&B?rvs;2^$ZuTenBE60O8i`$F~Tj}H=jZHaJ-NbE|Mv{COEz)Ryyii@hkW+ZGb zvQ#kb70+V!6&Zzi2c|__$?xDZOgL_^1G#5%V!RFISMfnu=8AFW!U5Wg(a5ScJZ*Ej zl;KY5H5(}-#rTMnUuU{%JPlQD3Jx0$7pW!JvdfqY{B{Oiv%0MPt8(E9B|-_Rm<_Oa zC|AzhaL0uLU`8c!O*mKAe)zoJ-vh;hzi;#Z5|~A0%{eBYHOV{Wl%;@?K0JbZvq}2r zwoQE#&C#GBYqVSeY_K@{-<;^N^N+Smq8jX6NB)qx{H_sv$Loq^_5aoodH(c2?F+a# zYZJJO=*an}TY}-xHIOgO_{|dOSq+f2)xV^^`Xjdum7g!t?awZ3`b%>+GN-N^rqew! zZXf4O((dXR1ueU*<0X-S4dKSzIoZ0lU-r`?R^6}>CN>JBa|AQM83jV{zrsE@&Ey9h z<$7@V-(XTX26$Kis5Bdc=XGG3CFZ7bbaVto)P3P4LStTJh4>*g39##npyzVs|4ux2XGOtqi0$jjHiU?Vrc?tj zaM)++BaVj`&ovjZJ>S{$843*AjTrb|IGp3wa_KU4((TOj{OU2vgBI#$c%9@-^`_e@ zP|Qj=DOt()KWKwK$JE!mN*>!bVt~#KnND51wk|EX#RPQXW`|xSRrtzsQb&JEA>kGR zOD(|}P^4WxUaUAEhv@0SqP#5YIJ|BF9;zqShylO=A>ezE${59#7Z*m8N0DqrvrmPP z{xN+_8pl)gR=j(aM!2`)JBk!7wNf*x3JQI!3ZSFF^;BlXjM{Plo+WM2MdWD4HfO<{ z7T7#MIfwnr(7U-r;ZM5>#b0F9SjBNr8Y%ml5w{hgOM%6SouRd{b!$FSmdRTe=id5zeFkC>Cf(1bhdwD zz3IboE^v1Z_1>CUFceBD)E$lSp`mCABXdWsyjvJdupiQwbZM@XwAS)eXp)c88&f+T zevrg}L&_4=>FZf}!mybp+gTkagJzWOrm=Bj?&GLt6capKEpl~o?_d;YF>pXXuBX$-B-uPM|Cok|<&)W(K zY-K#sqF_9T&Y!r&$GZ#tcKe=OX5%-%zW<;5vML2K(IJ@%^>OqBd8tVVO%7pM_c*Uo z@fn`LEI2I;OXj%Z1$DH3&!s&qzd*oy?cAwrc(!<HLKOSkC*nnYrgGkn!bl?)qSX(h=v)w zgP6rV<{$;=5?42Xm`sT=%2F8O{5tE>Sl^2HiXxpW^Wy6Me$*#l@xKJU@rB5t#t7u^ zRWWhaM85PnEkez7m$j;2J}4Tj&3E{|7_uSjV=q?Se$trxqrOai`!EGbg0ZQb`qC4Hg)C}}hJHHwrhn>MJgA5GGhmNB|qD26_yIkAZd5nzC-(S zu+dprb6{@9h^g!Mxb;sSeT8g$UjIJI@BIf44}@pOL*4KzpZ27fV!=(_*Ep$IVcE`Y z$G7{>E`S9!Po@pM{Bx=E9?bvRmDZZli*bdqZe$%6W|jpv)@20YD>S#~75}BA&LR%9Ftt?T!?$8}y5;=az>1xTC_)oW@kiZ@mU@wc*}(k#9dGXZ01T;I zH_LqkCC4U?vZ|@AX8Q&o=PG_|7)oFv0_z$x&#daVWu$Bj7TR2z%$Feg8uH#tgf0OB zcY9w)nTiT*cECdp@4cFjXm^ZoonT|GRNeqqV{k@u-oXR>B)WI5wkJ9c! zM5;anr4CO4I4=A@nb`LCvW>f*mq~SjIiNC`DkCzMGQ<(KYT3!+NOB7h;(*{3@Qd*P zO!bVtFE_w@NQ`H#X(bt6!^-1m0(Vc^5y>4FHj7-fXwL%tP$}Ryc zp&5wLEE!_tDkjM}A)4UwY;s?*(Fsn&CQ_T3J?}WQO^U6;BND9d@!4UaDNNGI#1T{4&<+nP5Pa$oCEwda0K$C%%rlJi?VvN~Fi#vWF1t!M^JXU5W}jB zuyT_x&MKy}opFFvrm`#zg%*epQnA8DKtjrO+Q4P0E@(@KX~D_}YAiDnOlGTs755{Q zF;SkOSY{FgvM)hsUxB{ATJ;d)X4Y*sHduZbZ|{@iy_nb&-thWKea*z*b%URj4s;?# zGAn0sty~z7(>2YTeI-z~|7!~KK1JYYJs!tp3q_ovlYUb9d3!e{-0;v*GeZxp?eURc z=1hlyZf39b_!JS+&jfML!}&9*{8_toskgIAGF=SzzJvVC-Y;oj6B4{`n2}Yu2I(3K zO+GUmmoH}(#v9z4i*lB=hwH0BhnZ^y2KL_G?F;vRCiQy%izPtkg~D!4OrsuI+WGZs zY@n(^+%d8xP@sMo^c=7h zGm^%j8utqaH%V0ifDy0=XliY9QxibO=xeo@jFO;3(1sCX;3SZ%F@d`usR7kY-S1^g zG2R@2p1?vEDaiQ}dIbJ|ipftaG%1txGy7oFu0fMx72zhyDQuVTm7LTtiDRVVO6!o1 z(leE0?S+gMeAC%%-EGSUEg}aK7qMoGrZryC^fjW-rOCF_ld92YSPWd^cQuozVCO z<#`G(@FWC~KG^U=gwSc~m$EG1=#o^2Qw~SP-S*1Dq@R;XI=OX@4U5XqWJGwrVN0zG z89iGFdi3bWWBzTLNEc(`&}wXj9OA{Gv8IS?jUQ_maTuI!o#8avgsO{;eM7Gvh$D%#0Y#&$E9aek|Ih(}$(d)mq2z-=uh`q%Yxd4_EAIKJ3HH;J)&pB@YI&~73)oar#zz@a zvB2n`O&AM$Q5LMa=8RM#16u&}OKc_4PA_S>kT7}%1}Np=Q6WAMWZV0!7BDiQ!$E`k z0LzmU%R$9VjBu=5op^%~mQdsBc>`u9-|H^Z$2&R? zvBu!inrJdc4Fgz!tCMT-Hc~U5e#nuSDYB1<9!PtfGMWD$K`FW1fRx-aJ`>aw z7|@_rmdj%k>&&f|irz?ilg)>0D<7%1nKm9BQJ zTRq|a{UaQsxN6Mjh{3VzNSGM#l+^vj;iN~ugZCz{s zGo5Yj_DH9~Q4?l@A|3`+9^BEAV-;I{8N0sY1(Jrf4A6UBljO z{d)N0xIamyzZ?7O=tK&bee+=7X=+;Y*zv60sLYI~+sr7o{j~kcIp69!u|Yc^sIu}= z7q=SBuc@W=*-F@kg$M~6VRB#c&(A3^j$;pgBEDbI^*g1OluUbd>*oj2OvC-Y@)NAT zn;U$RYEw<`QUYWZ@i4^R$Cwvug}etQMm=5KP=S?|6@lAK+7w4l%T{d}8Dzx^&pD5> zYRAZ|iwgtPjdmMPx`U7>uXY+cH5c1qjBeCc-uTRUvwPUiY;$Mf@3%L4lB z-||F$DZlHx(B!QkubUy)<@+O9pKJJvzfKDaKi-<>_b;!s&iGB*A(Fv;A9oxj{bfCC8<-3Y!X$a9lqMD z>Y-?TVYb|=x;~ODVfp=JrBd!p0P%n(N-u_}RuNk4PHwzt?Y@o<7MfJ>17%8qWau>+ zPJGhkcSDvDMX7u3>_*yQCL5|2Ya$pS(d&|t>z0f$BopImP=1~w!ZuZx`^7q7O#`;d zphEDXkPFBcOa+M}#c}BM9Z`K`S5`R7$+i=>(2I!t&%2xtdZC<_9i6FKQd_!tpaW+H$bt#k$*E|G2R4iA)v! zoRzzgjY2SIy&Ratd3H-#9}boAt}cR1JMp01l0(8swk`~JNFK-=U#zz`O@?$M#5a+1y6nzdcks6;pInuyajsb{#VKr2x*(Au6H_I%>vdtL8*NAF>7DDC_1vuT^`X*sANsL|r@p+uMs z6zWQSlxJ7khUt7^;ZRAqXo|1MY&fz7bY4*$;L|?FvIc2fD;cC{NJJvILFj3qHg+jc zQKWu_l;>y5#zmR6aNV%T?yB>xB;tV2u?equ`|g{iWL`y~Tg3D@;S?^m=1;iEcf6LO zL{sYH=kg^`XC+d<_R*3juDN&|!l*F=e(7=CI+9l(ps2t;Mqa*jdR~+C&HTgpC6A+D zZQ{0WaAT?W%#cn#&R?KqF!FMv3rRI*SDdhw2^bOYY1_dl@N#mNJS|h*bol-zaU^;J zEjy_>&TEsjY#?*MuwhxYZ}|A|0KP*e_oJEI5FbX}j)png#F^e*X=u8?$X8jDq(`mu zazNx5U?JsV)T~D;bJo#m{ib`|F(NBYU9gn*(bf6Obq$*ESWCLSa)$UG>`RE%X-&Rl z9U=4N`!)%8-2BG8x=;G3U`F#b^?{Z8rs%Q!+U)u+5 zo50{NWu`o9a;b>0Ny(`(i9=*D!G_)$!l{0fjgNGrYcW#{6x$l?OUUz+r?tt;O_lig4LQoA`|!JcM^!lkM<)FnZUTM1Q^;oNFZOzV?=;n0?!7~}9=L|{XOV|zHGZ)7`F z8w0d+LUiA?wI33KwzIUq|J{=g&y6b=^bo&eP`kV{^I67>@J))j6y__Lu_B7HC!JeZrH)pJYNNl7Zf=~bw^rBI*0#5SDe3|KlkYFF0>-Z}gjNhKIu}5GZt9j^t#W=X zzP3YD+1p}4+Ac<~Si)t~;p?C4OhJtaN~H9>7KewB@6O_|O<3)V73Unu+;#A@u zpob=FhYO9Mq30d@_C5uUgYMW$i%b1-i%u^;%SjE#LQgqdTDZ!XlfXG{`3G~Dlkw98 zP9!NldKjOlcXw>qM65S06Rxg?x;h}ebqL38o|*sIJ?|#iLMotu{Wbt!h=IdipMg#- zXvr1Kio@s09gJ5{9)SaSpc)~lg;CtM3PUT3n6`Y+2+ju$4XAW&*;nh44sn;pG_3=; z<#aNoowQ;OPC2Q5oUXF(nFOC5B&WL8ZrBWwt(QSABZeCG##d(cf-9Rr3|I}o>}s-6 zZfGMmtePV>|KwktB-O?ew#md6$mQh=7&ig?w*T#yfZIX*FWY{PdN_`Th%IT3KI5Ss zzlbG*hB|%_74LQy1qjVB;4@sC!j(BuSQw%oA&rPmkit^NqY4c&=&q9NKMd!;o?8HJ zu+N5uhEE#~y?W@-fpcfjY{_v&fuq_@wH(L{H}m9`a%<3G6Sf8gF#->xrcioZ&`7Z6 zJ@XcR(!ZaKDx3lP4{CXe7IqY$Y`~`vABI#FC`1Eff41wQE96%p?vF2!mZW~$A!RT>%Z00A09SSpQl3hDRn70j3B74d;^-TF`z;1+{e4g z$!drkU0_QFub5XmYPW+Rp%T=karQL1}S0*98&8chh zIO5|VRxCzeet5V9h`8Kx99eEamO~d>kTtL}W^BN*sbLOwb1e3AEHjNEaQRxB#q0nd zL!5ud?Va5H&=aJ6R{U+rR<~kf%M(j%!IUfej%G=T2U(K(;vVj9E<@#piTM2f&tN}} z3HzDRL6FGuPzp`t0a9PCce9oaNe;42)a_GA%^AvIMVxY!YN0(-g;9>) z>Ouq(mTR$BVyLUYmf#F-4Hh)`DeSDs6zf{f&o7^ayws~OUyxHc(#)OU;H{GgX7Fxz zjd@QJ6zx)UFvj3B29l&6RMvbYegU`}Ngf%(3WZ*{OOqh`u)Jbk056f!a-NT610p;>`BeG&NkB)X@rs{ zxaHjQBQ$fsGnJCtF)}k`eI3iLfpTAp_oDxJP#|bNpL;5n4RO6ztT9f0>)9t<;B~DR zfGqnSX3_#Id58y7RF?SYthe)>5;k`y7M^1`)1DDPNCiGdRgd0$XniB}e>p+FMvLFy z8zBG3tClRNkM|Us(9Ok`eU$?_^=(2RAch$!v1{8&_xq?dJf+Rf0Qe@P>+0$TMhFBM ztKlU|RC-*F(vZngq=YAtG*=Ufy)2p$9|zRX4pkWpPM9rZ^)0lul;^eC+?JVk8sM2e zI1*%`sEnCaq^i~Ey7Zt4P#;+n#xGoVD1@yc#H6m94KwagS<=&TQAb}{0wNgTxy+sU z{!Y(nSG+F@CkAQPb;>e9XL1Z)Vi%x_t&_&!a?une+b#xD!sdGQZVLdxegdSIUPmWn z1!*>)FbX9@y8hi<+>FmM5r2&mto#t8G2C00CI}oLjmQl~;mnourUTmB8K$^&>xx=) z?0O;i*c+$LTR0j;SPfAQDJ(~MdT=?A6B@lOn;#hh+2}0I50v+wWfkqli9i7QAMy0+ z>nqSh0KA5`;&;(NRniA9$#&J7<~Uo<95Ri|31leLuh9*`+VnN=8?}E>P&LIZBnd+h zU0FWGj*6s=mMj1~PRx#;mKGRBs2ERRyuSH`VdvoRC95^{1Ij!4n9k5fys_bg{adDP z`yXFlfedM1EJ4SHbS^&{NLSr$hDP1XH;emIKEqxA`mJhm_1o)^t2MTowDP~@(TNFZ z{d2B@g2}T0(H)Nr{r-58+CvvUzMz5qX%=qwGl>H;iwZ$_tGB8{4223;teq*TI6lr= zN8E`QkSqrgEL+DymZ45dE%SrQvd^j;QUSVM+?HEM2c-R}p;o}-l3?*`cejjEVl#}G zx<@Qg)%hJ&%Z!|a!)_B6jh2;+I-+54OQJJd%+)qL3RBSG#TDVbx5`u_4HFboX0P~} z%@Nokf!>u4g$Y0IPv9d0m!W6L366AJ*H-`Do}tP9%K%ha^48W`2o#`WdtCk4UgO`h zR{Dg4FfkMjT0JHyOhl+l!omHb7FmtRNG8?rl)op_%%Kb$$$3ifiRiMp*(vayy^Rgw z2S1k2C5RRzBiTxU#QIs1s&Q-0iv%CI&z!3kcHn9V%xz4~oL7r-ISLI%dI=+i8k*Vp&S5D^JI(AAF#8z3x@FB3;{n!<*#(fLQQz~2{(_V#wLGXUztgc-2jZu5awANwO(DLS{eeN`IGYHul8=u(xeUgg{Mww!6xd*!8q>FoY_wApubw(+f7YukrLR(89O{lg)F#9wWrPm9s0Z1lw zwxx(|<;{nYX75p6fr2GxU_YOc^U3e-y`j8!4ijQ#YHS!^v}IbEwxrSDL>f&zo0l3X zS8*KJZXNVq#&c3bR9Yc)%B{jVvdY`%Bmb_}JJW>*Kmh?X(Zl>|Waujxy1M zHwI(el9ilLewF`!JN1S7=*@Wb-y0{ujY{FOSL!*Y@TIk_5(7ANk^PN^ZXcFM)2IOI zMXkQrV9%0GOIMdIsCaHJJ%mGxbe6bkUjP?XVvsCXSuZd=TOvGH|B*8``NY$h6<=!p zm}O2|UteESvp`eS+Qh_#EwgWg@A6Y~5VMy912dU?D&nb4UzMPrPM?G#EpC%I%xYPz zH!{=d+uLXESEATh4mIdhEKn870-2;S2<5~Tsep=X<1hk%qJ3A562cm3l>QZDg)j^> zu30PDaHnm}M6?W%dfIjqKE%D>r|#<+$<^eV4-?J)f^6Q~ch?rhoOu7!RVeXVYKG)b z8RDr4M0TH3Puu=I)F(DP`W*zg1*Eg{xk;~7rl0KmYGcHzjYFHA((vgdCt-$vHCIp) z#Ne#(n#B`I^%@b`{?hE1(^m|iuh87-qO>hH%Ny-|h!+av>o~{7 ze|cNc_!IVr)_+TXek|i#*E+s7A(vehgQr2Y&he>z6GP zdOB7u*}?{QfrMtQyf-C8dJ!o2+_;8@o5c}}UQBXi6x=>oYAr1#AL+XH#!NuW_CUj9 zugG^BaNHqbIDo;#j#FW7S66=1w;c!7HUX6!K0VB|x@#vIcrbmb&Hkx2WtIxuu#NW~ zW}|vx5I|fPAyxZues$#$PucdNHR3w&4HN8$Jt&3Gg?adX5kr2)6h7Et{N$*1w%G=b zjwxo@)xkkFF*F$Lc^}aN#{<32BjAmQ38+6b$`}N%ua4nr z3wcrlj~O5AosC>Ea+W?^=3Ta)@z5EH_n zY}y5-_3l-vX)4xapSol*j#vM`nHG7KD_OwFaN+*fjB|)N_!6p`>Th}j`nc7M+YKdO z8OTtM60#IAh~KYOiIkZjra!-%BsXg2wqA#qzXbtg^a_krNCt@k^)H-^%ye;a>UD4oBYpeJ$6PyUT0i`J;kdR74K!GId48fZs$0t znY%t5twSaX?Oxvu=kgOK?WY52kvelCUVBL6CN{0t1s8&G4;z>tZE8({<50GYJz`H# z(YEl^UsDcFBP`&ncZm|t(kV+`+1$B*Ktu+sEmT_}4A=X!am1!mNA*~76Qf4hVYtx{ z_3Bb6D{!qc!Fzh*lxV9Q*&-9W+o{6lPKi+G?}2G1R!$hEGq_U`IFv-AB4||YOr3l{ zM*c84SeX^vkrKsJg*iDfy=-&z8A%uGL9csH`P_OWYhB_?J@<0kwkM0acmUebujNpB zSV?@@$OzM{3QzBo7lZOFbg{|CEnHl|1I{9NwSD0cPQ^Pr!8GEhoDwpTc-TmRTHJiyH zNCp(fh|ymSzl!sNJ%gxWW`)EQ-w~=qfJkm3t77RV<|(f&!hd!Fw}k)1*7D?IsSWis zxq?rlDtRsX|BmkkOd0Gy+IBek?Ey3l(-^pEI2w*_lBFd*XO@~fO6O_ zH)LrbqH=q#CK=bw1Ef|Ii5|9lukm{u8^1w$EDeBu)e`3`gEShn;8S3UvE@mQl}}P> zHL$VM(9qG(?kUVr)N=$QM1U;8Fl}&kOSynCA!EpGuyL#cOBeJi+;j)<^8$SF-aUwC zCR$(}cVEKz(M@OZ<~d&F4x>wgNz~;^ZZb{`6&!P=2wgG?vxlLnyR7dHRjtvcu(^&1 z2Kdr6bL+!XcG(|7%9c{5J!2{(K`_d`O^9Y6^g~#A-&yj-g&mkYtO1AD>gIajx4tES z3ocnmF;^g$2R8-=^^vL1rOnoWj-bWM3qQw+t0nk-EX%R4zQ%0plA}lq>3FTpnXRMi z<6}LFycEn>wbGuQ`LY&icUelHA@#Mb?IG5|7y59u_wVz@eOHFOrmzu&B6EXP3r2EJ zszNWIw7;qhm#%m`Y^lV%Nu{)@*JUhrXV}_(*?Ca&@%eTC$9q{fPjW2;2v;5T)%!V5 zl-MAx+Eo;=#f0lA_!sGC3Cw|;7=sXD@3fgU8*~0~GK(p;gZB%R!Mu0(cZ&(jSvTpH z%O2&v{{CJH`R)^$@!Z=yx3Srs;ceXk)hZZjmi>n!G!CPBswT;Ijx0;swP4Uw?3W(_ z*TXh|WY1#T!9~cB4e#Nd`;Qmz@Nz1!{6!s-Wou^_sSVvgNn?-i#u;(idO35wcQfCd z-vc)bnf?Q?lLBjEV`F#UnNYzS^(djQDreDEXGh?QCR8CXIN=+P&Zgx6^06A8>qOTU zvD}a$QR;$jgcMk@MvDp5=@as0t?A#32iJ9<>x|iOh&aVQZh2 zz&ST_;FV3WCeU48o6K|)1fCUkNHI20(RxrfJ01>6`IRYJt+PPJ#mk8n0>`#**!zV7 z>UdIGc)q6`6o`(--B$;|LWdW&?x)>ME2ClySybx=%^JOGS+4WPKjCO2n31qb!_WccUYtz5sPx4ZDy z43rD-kK~qNX~mM8{|Nyo!1G}g@5Sdk&pZFmMD2>r?Q~%AZs2(M{8?`+y@`etu2CH_ z{PT%GU38Bg%bbwd_6+=~Z38T5Ac*|S=lS8nym`&Kl?m}zr&`}&z~6ws0zea%z{||v z7oU|nJrhdhWmy1!4ekQX`MkY&!I(IqSfXCS%7W8DB!l@LS6iVHx?f$1h+%AExW<+N zlwgYN9y6#J(AbwPScnXpjpo&m@XbC7vXsl`#>o%!ojKanYd;#MBM#s&A=?pTcbm#^ z$InUcRE_GWM{~lpFuJ8_W5llQHXtb@|9ArV(6l!G0V-V#BW6}h#^lbQl1CI!;6ys2 z_?JTZPfx8EBX&5eU~Lu9a@dTlJFqwEvO=EG0M{Jjz|KDe_lo+WUGpTK1SgHB-!6Ao@qG_3&^H!WA!kar*DgdE-cacQlG!d%7y6j7} zqM0ylx!(o&`7w?eRjn2q4$D@n)TwHZDMg8FkSVI1ByQ;KhY^aU2GY*oKYy&XKVq^Q zVd_1NmMyY%aSjklHPrA*s|?WXd8pKvhxr=$!MeWn@T^+7$(f zk{Zfa4cX|>ne9~Tq0gJs)!yPJ+1;XID)Wy{jCEoao0hMd?6xiVOaDV3%|%?gl-F{1|-_RA%D?qA5}=-Q(e zQUp->?CodaY?mNMbbRP*i@$R+-R?zE&VM|^$m?lv=t@mgeB8u>po>_%pW^Gh%b?gL zEs4*cEk7C`yd)!n=1Le;iQ}IEdpqmrOUT2)P0<#kBsh|8Yr`fw#t1_a{XQ3` z2yjj)P=Op(l@m+_8-RkVc%PmXHDUwb>tTQ)04h>6x3jC=vi$bSI?wkQ$90^R!=Wee=tPHt65VNLu;c;XI4875P$B9#fSwS5FZ( zKH+rWX3>6@Kb}HXr1;HuhXc+!L`ONQ)zFF!I76-I6Ww<0Ff1EtBI-VmJ-t$PCD~R6;Y~lD07o5o4?dQ8?*gx z)kZbn0s83=o*&)q3EV8X`%Ca#aDEBD{`pOViME=@^8S-8OzU~OVmzl+tE+bv5@l)S zGOGE^5Ld-X60J-B&G*bNcO|hJx3cXndNeBn0kQlC_D?A<-k!>*rfa;`PIf*mYF;}p z7^U(&rDv?XPWf(SZ3ln+Pc74KjecouFjc>dGBHr{Ki=7KHm;y=<~Ab{QblJOtAIu| z3Qtei_JZjA(eLJ|S$mNmxh)7QDr&6xijMdr!t-jh%RXhO@{dUzT<7@A-qo-axY=Z& zyCTEuda~iQZrI`1{$#VuK!2X(0r`omon_rEg-2WSRF@8O{KR)ZJT)in0owigiTt>o z{g6NDvbj_2CUys9FwS$E<(4~)+wSeKt$mSZ4w>g@>;mT6dG= z$35&imMW~$^f+imqmF|59;9D4Gt)Xf#SDFmKu!ZB-dOLG@c{#n|!L#)PXw_ryAWy2P zM9Z!qG~z9_Wmbs^T)IFD8!XW$rOQ$#(oK$t@KH!0roXB?Nrwe@ zUg`+a$|=$gSPeW3tCGmAOp)jQTq4x+(Qxk@jeuv?Zxp5{UmM#IBpWdQ!1Be$Kv7i7 zsSSg|vwnsIAHw-REfX9wXjZ>ilriXH8p{S3$vSww24~Yp(p=KYW7Xg{FJk1I8-c~ zg-|jooGk1P)o9k?d&E0UoX~-3NpgrSg_=Lj0@)T&_EBA@?{(O!@$KuJ@7c(-&y;h< z!~XTqjJEuJOx3w&yq#bfqv;EQHb{0D)0?sRHTC&`g}KpFUrn=h^(JeOrkTZX4xe}w ziu8U=IMD=TTZ6d;^9w&kOGpKY%4jc;ud4PmQZ3h+i)Y&Wc)w7hH9lbAgt_q%{O+cB zH9?K{4_op=S`ExRWt6b_cP*n|R#hyuH0~3E9VF_$PZIe>%wixdQ1#48qc^KIzt^9O zebVjTJb!lD_My6Gf^KE*(}-}ZCF=BP75;;LgEjf>hTrKE&QYU6Er={yyC%Mo-1AjsgJ2 zn-tjp#mba(_UA)!#`zKVaoBYJUY3G6Fz;HE;1fFkpW}aKcTgYB7f(MkFE8A0t8_c> zf@`~@oyF7XE2q2YpnZ~(X#jKK>ShHd)Sx39UMD-jtcvK_*S_dJYke5?&XD=Px!1;= zEXaHjG#>oyQ;73lPk6q#xwzc6uISseZ|px=FrkMJGFyFbhPSao*xv~p!d_?Mzg?Ko z>1%{sn@A=>0+jF zIZLzPOhD+F?DZ!Q2PE+c5^Bgl8%U1}GjTQ1vxVTUif12wxaR_=r&@`bG^ulOT(HH> zo6b2K7-D#lLA>SnjSPIX_32LajpaI6pn8OH$)hbwCiDeTPeqp&&x%s{&%{bAN3Brl z1&7G_HjuM06SpKqS<9tof(<@;%gG`ZtByHdQcBx6bqtn(@@ z$`|BAdyo9er&h4A);yH>$)vspRxVK+spc{~w}x%?{q6+;xPEXS6q}y-Z}PKbj&}-u zk|Nm7sDLA)C#a3=GZZG~)B{xQ2MmcrF70|1YRke1t zY+MQvqOpv^OJaOi*vB$evXx)Pe>xfIRCdf|sB%^kEB>keWNo4{A241T8*TZG9JT|W zlP5!qZ~nrSOX(g;^+sBOEcL2VtuSJ9hykVlCAXSOmbP@5QrWCm_rlCNRGJkAhR$u7 z2C7`UuK6o}_m$5BU&?u<<&OiEmdrCm*12f+CBU-OJ zrPJtvSXGLhS5$lc&8tK&9?R6_=l2hSE;ciFI6t|}*C~?r1UVnjy5haj)7Ebv(iaTz zjs^)Hl~Z$_+#kGc^meL>=- z60tJ%saI6XEsyUejh-M^JyOPG@AT3-keZ7_ZVy zL=8DU{yIjOHn7T0%vuq`g|Ke25TMQG3!tZpFb5L!eDi!*pKqS!M^*@z39P`EC!mUyvSNADH$yw$f2rK5* zL7^Mhr)@@^@_Q_unyXJatfCIYO*;0aSs1`KI!_um(m8ebwDTkMA%SK$aqpGhM*W^g ztgvA<757TpGRl;sY_No=Vw_mr4hNmuSUCe}r+7w8w|a$%gl%s_u->`lo#dWNptS0X z@eoN_#(c|PvQVsdqWSV8rhg$hKly5l1kIFGN5|hSQ|xD;R@Ev&K~^v}4efGdC-G;! z?t)X-e9G7+bJQYMMzDMeJyXk;o0Q3>dtr6CzzYd!uD30UcObRThvdjL=&8Og2`)If}Hi5S@NC#2RA{;zDH8K%t$@E9P z`YYhExl!4V7r!sKW7pq1322w?*l}N)(w-gN)Y#Lp3yRu6)hCkqpq^m! zR&KXj!~92NAKj|E+;3ZCuJVt*p8^5BAD0ohqV%rESscx}|_3W*r~QiPI|8((5qhG9<0oLMCc2=g>cWx1VV#!No_M)s`jEI;Mp zDXV7&Pbxn^zg{xig=*=*Y1&zsOHyW4oql#bD#|~u`q*7S(mebQf}#$K_q6VdES&ZH zfjd~>HvgeFzYfi*pS>arotpo|2WY1>ZmuT+V2uRw_ddWAKTgu4V31O_S~{WQ_?JCR zSdcpF6Fz6LvWvj1{VjYN0CocUwE>eC78ag+?zu~sF5S3s1Nh(X_Zc3;dH7vgL5(6O zp-odvs{;k#UZ`Ysb+ty}kvMuSKQ{<5$#7U}Y;JCLyWPM3>%V^Y-Q8hFTzWqI<~P3y z59)L}PykBy`T%Y_lM#UH0UJMSL(V{hPk2zb+XI5~<-XG6Bq!iCAhx{WbeOM?b7L)mN?-yI}63Et2GY= z+{42G{KJoafIMt3G+Dp_yoKQdPEvqw4)LX2ahNb*6?KeCr%ma8c0472Znj0xQ@>7Q2pn zCpl=jy^$pz#ydUZCWG~e-yF?2NhzOrPVv6o0cI@qR5C_|4QXl%+?Vt}{UYVzyL9qX zrH)RuO1xgZ7j)T_p8;<9lb7@bkG@$tbve#{O<$=!EZUH+@c>m@v5^v08dpOVDlFO!$ka%3 z?3+)I$P7Y?EtOKp(&TowVub|gXWdv!lPRv;TH(A)dY-3Rcwym+-bTnw^Cr#2dVr0T zX^AWQuht0JC7V`DJs;4bhlI3J3+fye=X%W(izVX1JWKIDAP;y-a{XLAB%$P}`{d0b zNuVB(<{2H1F@oegNSRxLWojjSrfc+ZBFE)GW#u!GkJ0^F{Sx8pl>2YD?}e|m`}8?& zn@@K3!opn$aZ#|bIk5)4n=z^0-F6l}27KVw&%HA!<%IdhoYWJWHN%o*TdDiR3J6^} zi);hzfhm=(8>&K3VlGwL3dwx=6WRDUz}T!h^Cz=`tN66dYL)XYunt*@I#uAVqG@G$ z^F$iJ@;g7W&mvXDtLS6jYj;rwP&bB0E#O3+p?dzS>u<=yYBi}cEtGF+w5Y@{8$ zd2{h28ysb8tnCw&OjblL8jH|tpyq(H9XGBq7BeocZXZ zk1kxe0L5CZ1G1r=V0$|{_gMY-aY!#m#zYq-nw|{GoSfPuiuT62|$zX zaR=Zrz_w&Mh4Rftd#aKsY;q&X)LIRP<3WEi9wliKDApSCra$|(7WcG9HsVTtc@IIl z-<0ufHewdv8av^D^@|0|XXDsuo+641m=$L^_$1dbVXzkKt5X%@3&-2-lq}KAo>m5w zd>7GQpsef(KoO>fvhYc8wjTJGkmfUcZ}6!phC@Q2M!4N>8;H!Sylb32b30NAYznBx9=N-}Lb$VHC9@Yp`$RWzyjywh zyES8f7o6Hti-#@H(Zh-xl%U?C7Q_@8kHd>A`?H)ZD?>YDMb|E>(0l|ehXzFvdD?1J@_t|v9eZ4$9c@`^ZlH_4OPXX1{K%)V|GhYJf_bylnt_}B5CDoVe&{=$P)2{tQ7Vy_&h zI5%jjJ=QlGF~`Y+@v)H0aOn&Olje`3Z>$tjRFYoLRp$I+NQa-LLbXXf~rt-%YnpQ_}ey>({5W^v%F^<$`JIAo${! z)4Uzd`O0JW+hixRewSH9EA(%<*RB>qnON?MLJ+x;Q1wEgitln^O)CtOd+AIRn3Oz) z*1EOf5X=yi7c9tlJNc+y&)kRgbONsjBg^5^sJZ)x?7JhJueosE`Z)vS)amZ!Br6Pg zR}BmG(UIis{uE(BLOFPG6}^1Z`B9{yeNVSX~T-yN8|Q<74=sD0+LLLLO^(k3AZp zYM3(*m#2!bn@J~lRe`tWld55`UHmeM7@-}R3C^+r`eaV8NLx5vIakc4yc8`-hf9LN8V-TA$GtwP z&eu1VS65eohYJe}aXev;S*@efHci5{O)%c1b`9ZUhK0feh^9|Y;O<-8Er)QHEL({X z+1H_JuAbI#(!>%A+@+XTIolZCZn1p<%-GL<_OoCA`qyC|{`}|v&R*p#Q89tCbsHGZ zSARsD{hlzoZr4*9Dklwj=zgv2Tg;7tJ<^!Sh8zz}q&oUjs?2~=3oh-aicQK9otc*+ z>K*o0U)+d?V>G=$3-AP5N@$w(8maH@-b7+2#|nPqUenI8r9}p-L6UL)f`x-rdxsIg=>i z(IT(xqe$7P(zHkI$qWV}f$DUTtRk0WY%7n5anl4jU_9dLc81AlDBVRRTfVcET3^Io zBGiu9*Vtaw{-u1(?JsF=o#kv+SmcO6~qYuM43@3lzO@YGpQ|<5k3g<6{%~4HtJudL6JY zK|&f!GyS;NWe{#{*Oe8GD%EVYCX*q;DgYq$g@e64SO+g&yx6GK3!9tMkojbmMb6b4 zV7Gqb`Ki6&>_een_Mlq=vmRdK zXJYY}GHOR;A7#_J`#^ck0igjr zqXsxXv)N+(LG+f_ff?@T7iI!9m4%V~F$RuJi0lZmc^>De3`iav1hwfDb2&~X$!Ij> zoe(WPfknT9Jdt>zXTTqk=uJzVO{7gp(rny6MPa9NRIfGR41CBpH#dSXB9McXA0M+` zj${Wpc40MvcF)9`aabD-Xd#Szl4|P@R4*i=z)X6Da0Q4{jHn3{4n9t>X`^Tv&>qYj z2*>0*rxPI%>#Z0VCnt&m?zdLTY zpoFIa814YmuUd358KS8t1~7m?n#PJcL!wZp4Sf z_xN5w4seOT2=HgO+iSHJMxzP*gBxMgIIA#wOTyX1!^7`?|N93A-QWK0*Is$$mDSZ{ z+*i}<2j67?w!L0=FzCaY3U$I=Fl4}6PJ@JFmjr|Uq;uHq9`*XY@njM+9*`QI1$wUH zOTn3bm^;FB)*j@(cNVfrFF&`1BNntPL!t6Kt25CpH}Z3z``rHi{@&i+y?gft zeH`w<%njJFqG7Alt0-?;3L9^pfvCl!&n)g{<3y%9S{SJV6>o95MdlV|t&Mn-0JD8G zqG&S`-wfbA{K;TcTQ|5arRJD&TNU?#(e>-s1!fJN(i<4l_pb>{j*2JTdD_)wIyz-O z1f20KgCF$euzNMzR<6N*Fzja3ENxKgm+roAmVS_@!F)t;0fTfUgzcI=zyS6sw zyDM^_S4Y_T4KPM-@TWo=4Lg5(=(Xc-KxiwGWWdSz(ZImaHUKaNaMImsI};@nSMyLJ zPOLTD%{_04sLz~U!Uez?X9}uPr)FoONDewx6d)NEHvpZ(2Q=kJKttu78!=*{$x%&rNY83ru`iBrD&WM3cXRbVqIRgxXtzzb35qP zk6&&AGb%}~;{)4$z=DgrhgyRcuUbl1VNC%15A$MAdQ9Oi+5;)pW(O$Ri&#XJLr|EUa2nMcyRbZWq=iXD6*SY}_8M%2?*qVN$`LOG``eCoLKY zt&=qe;^LCMva$j-a5$4NtUFFYI1q32;o&;I7_q4DE!^ z5H#cF&703%``kfix3#nk+ckI1FN}qa3&M+o<+EK+*vZX(mZ>fGY80SsVT|mQ;5CG| z%aQY@*l%{}rOEaIW}#5oOpvLwnQ*VtZ{H}mQ!%tX5JWB5hNoHcXsh-lxIr~2dZYb$GldA6i!O!aS$K4 zdiy*s;Lni5DU~V1Y+9hgN6cI;{8<#>26>|%`(m>A27Y0dzWCycQ!>2&pu5d=N)jX> zV`?%rIWO$%=Da)Ea7&Y^+YFXAofFP(&DP+40dt>c5|q$lLyDe|8$*FvjSUx08^et3 z+igWSuzcOV_1^#SzyG|~!}Q$EI(_C-wwgdj!>Y*RgaQB^S(HA~K_la%%yM(NvU$tO z!iJ^*fV2Lnob7wzJK^pI%(Dc?8?gIn{wi?c)GWo1ZyK>$?{iv*+@65oz4Z-FKdpDn&0m% zycUyQ{Yk@Mzis?V@Uybt9OH6xn$ASd_ofITTyLxV1}pn`+ig>7!gsNJNT>Fe_%(&C zF!rv2+A5CeFUZ0(Nu~^dQ*CV<@JDNDp>5)orw0cIIFxR(WRo2i3$S^e*}m8*q2mh^ zpKB%*z8!bhA|TA(FX;+URF`T1LfXUM?9d6@!A>cHXp$ZJpUm7HWL%tT3`M7b1sd5$L zdsr}7K6(Ts-s8uQ(+(~jIdUY;+Hb%8_QLYgcfb4HwY7Cvkiih+!o0jhiL4&1}MS4vVkbi%3!DxNW7jjJj3Gm> zfZTuoKm4~a3lQ7jk;fl@9D4i07rt=f#EGx{&EFtP=YtVAA?Hl(XC>#NJd#yw3|G;V z^)DsWL<_)`R73JzZ@pJk!xBx)Y)OfDsngJqretihvK4&|eODA+;ahDyRL2&DUZEYt zH3cp|u}u3)_C>V1s1k~va-yMtb>o84%#LWST#Ygc2^JbRg@+)~T?PYhc^o5MsEWD?e#dZ6Aij~FIP=-d^fk~YN^!nd1F?HtX@qRc{+QyE|N1Zy+J zy9v)l_JPSd!jqaK|_u%{f{w`A0Q7-t(kg9Ry#wEK&3dGE|`@F|4CW4s0g^;?N@?gcv1>Cf%%?!p(K z5pYh0rZaIgs65Pi-7ak3_SU_vtsPAMypP_RDzUINF)4PrxHA&sSmmW$6qW17RAf=3 z#3~8>#oWl%P{UdZdA(EzDUT5krHqW)XoWXWJFP=O;h;Nr1ZBxBl(sy&`Mzs7$M!diG0C4K73CgH|DUw8;U~ z<6)^P(DBlKU`=%Mtz=vlfYXd_BM^yD~Ka(c|Cx0Ds{I}n=ZE{ zNyRkb)!CjZ0Gq02MK)XJWl8J2v%96`3YjAV5bL468Oim;md>jjA*==9gpqzI5ky0B z$Yq+OU4uLpT$^mSPikRTW|jaPWYnTTM}4NW>2(2E>jHfgtw_U4$@ro&*oyAfg&jc@ z-0LC#lLf;OTrVi?IJ*q#{watZQwsMwAK8Q&f zyJ-cNyp%gfR-SD{wBCgeQ5@*I)$VYiAOtE0G^WR=n}SS!2=|;kc@oAB%nfg`r42fF z?i^ho!y6gKWc&0wyV5bKVDWy+QHsVB;41V*#>I@XYW?d@f`DCw&=mLt`2-~gH{oQV z30e8z`*RC42E4HFn3FylLLH9wCSPP zTd;{GLZU#@zIyfQa3A6BJKuWgzy5Fj2;|=N_4PO3d=owk^2y}4h%=;(cGsH3C`!@* zs?q%Jqn}$)v!?o3O&5UWJAx32xUht{RxKO@I`p&2$ngRuocFTTLbXCh0%}U2mxgEA z#VL#yPt!C3xCTq2%tCn(`pC}nGX8`@Zy4Yi(~9Fk3zm!dmjA!6L@9u8n;*cef{Z=f6o(+o;qd`ZNVLd64iKQ-Wtsnry7eGGH zEeltH7qU5XK{yfG-(HtI?6iBiDQT{-XEaYTo`O&T&Mj)NjR4Cwt5|M*!xm>u zC26x-tBMg=iwslkv@8-UU4wv!Xe}eVsJfL7O;rqw7t1fUQ7}p0X+!qu@GHsTVR75B&sXUL6- z5r@XWjE)^U_UyCIzWdIVpa1-I_=Q8MeRROCk#99l?v^;i02RzjRL+$5WhG~(%d#f& zh48=0U6s7>9@^>^`808dLoea~+2V@p^amivqkW%}fV0nZQZS`QwLSZ~f&@$>HbhfO zeI9p(NHXqvGzi1d%E?J-42V}k7sb$Okj&R*T@#mv?@41sH9bXYJs)C{iOP!kB^-`| z#Y|%oy)>kE$oSHzWR+yCEGjUfl7L4P0meD;7-1 z<=v6cYsVOt#@TVBjv4nJ6Cr^xQLazI6~<`gUB%MNI#)*edF`?#w+N>V@=j&l^qIQO ziZQ3LGm#(E3bzV8b@7yt*qnq4v6wdt7z?1j@G_hEWRkYKAyS$Zpb1BU(|<&6*>`0! z-Y0;eTzeEVT;$`?5czL3M~o5Iw>Ybn@k|?mkhUmfE=MmdG$sN0$ReN0I9&S;;!>Q9ju?esqpqMj0EL2eAWBb?uw_E5)Zp zWbHG}9N>ysW~0gVkxNQbfX!rrJP?RI8HFLi4+~3+7cN{dWLE9<=8(82Qw?FggPh5HLdaIqDJ$Jl6mwo?--}=Ujf4jRs-rd^< z^t->medFf!-~R32`i>Y$Bi=4+cH||}( z_TJgkXYSm(4Km>*pX82XnMwn`rWq3dSrZBLhJfHId#XQcp3gNT5bktAzDf}kb2>X1 z`2)-%(YBo2dVz!40qJsc^Dg_z!eVT1@4fcM+dxQQnm}4EUHTXZrHji)uV23oybfjZ zM62o9haNh6_AI+80+R$Q06hbTgwj)%GSkyS<{L01g&rBVv%UAxXD-5!PM%u5dHd$x z{wB!Y|N8&@SHJdazjpHEDu~nTw{9;kF1-Hw>nBg11U8b8XFeQ`SZgqu3?`Eyz#zOI zUI(AK%Ne($!h#Zzz&V6lEoTy@gZHH`ed&+>=#P${S-x}U?)-fJPyd%cU0pfy{PWL0 ze*Uq~{?gz3>%abMm>uVONmG}g603#yB<8>{N={3nGmhRSVIo<0qs9+vEH3?&+f-`6 zIAsKehyjZ<0iG={^1=mi2nYvi9LAVpbTpcfu^L?!y1q?}1z?Yq6n5wdi&uiBi@PRl zmWSxvLn8;$?rGXj{2ZAzLK%;;t0GJdrJCXJ(xporkmlIz!gHp7g*OokN_ueolf-pm zQ^+d9xh+T+gF1ZYhokWp;0BwF3b(gE+{E}scGw76qiOwV%{%mLz?_^9iu9n}er0;_ zs-|TOj(eRqnkfKJkrfF6qE!m;as4NUtX1LIQwBvuj)dpPbH@kIa+p$E6h=Nc?s5>C zZ~(9g&T*JD8Hehk4$*6QGJ=i9grtghnq3@-X)&&=H(9n3s#PB?1e*oJho!QO78qTjNIqET^u zoKptPVqBn|^)VH(_4rlO+|ldXP#9&QID3Bo)G z7-%#ijU*rQ(P#i5Iv5OTFA|Eeqr5W~b(f>zgv4VMREC4`{@!pjK^f89Bo}B7)kO%0{GIDa%nya}~c-Zk~lco7c6xHd*y$XUVLB z|4iFPi4MDWDF2!~F@Q#$0aA*`jXW9vlJf~$8Cx-DmZ&d{iOH_e!dyn*IHoTevLvB2 z>k*IxVVV%bKx|xM7qzd*b+=Mf?wa7b>np`~f;h!gBO#kEjv>dZz^%Xc-g~`X@0ULJ znQpKBop1jPx?eidUs_rMgd>3%Hn_F3@Dsd3OvJY~X4s+;rXuc{z$*sDLPANsk*8sm zYfN?(R)CR8VoJfyDsk7${*Hb7PzRXD(d~7_NK(Zbxb8`fr@6rSUchz?Ff~uQZ}or!{^2c1ny2z9pG)|CEMDVnY2S0Z~%N%qOJf z_s}MpjMfw(!=w>SNy7YEQvha-d*!|K7!!%|D!)F6vQa`HSP$A+`nin15644kD4Rs0 z>^u^3*%9%A&L~w6{NIx(;K{@nF;3!&GApSZPX3k7a2C}WwT5uoF%TEZOLM4g{kW!#Ch&SaaZePMkUgd$hm54-;gSzo1Q)b@^;U>%@dKq{Io)2b4<= zuK;C&drqG|{rS&-{>s(2?%ur%%lO)Buid(}u)4a+hYMcHhHJ6G@+s#0Rcr_1JEQY( znKzDAlT;%CALNW^AX+aSS=rqD9<0EvTeq%Xy#`zP#N&^ztgHY)!W9tUd5MrtSBl{s z2D^R$jnA zjZ~VZT@iFy{I)R|UIgYEPO5cS>r-FU1F$8o<`IMp9}D4Ch2Z z1ImQit(0;!kU_L<0>EIm95|4rZ4<#sBs%OW4?&c;UmSj)ly+A>!pwq3{cj1bP6Zn~ zmpAZ|H8JN%m<6Ag=&4aoF!&td7;;Y8m6WA=*%?YNg5XBs?fEA_dQ=Py)%`6rotoWU zG-Vw>ejKiBZ*LpLZq?46?v?@A`%11Xr3ADxBN+z26gMJ|m{lH4q71C@u5Em&wv6=_ zs1q+-#2DlVgvpiByPaVurPv-!TFDAKTQvK^MMQ;m4x$=spp)SBgn7#el~S3ABy2ei zatfoVb@~*tW!aZW_A+Q;QP}YTh>exk1y?IITgz48m}rIXjm4OvUSc6?BJVw*;SC|L zAV=WjVnb$4Fw2Wo{dO7Sl(b5xoty=>psiN|Fnz`pP?~&d1Xg-7#A(IDY(1-{LU6H* zX+`AzG*~dm-Z%bEgOb4_7zXKFV8(;RYS@_wh4QhhnA zqSGHh25#2l(y*j|wK@QU6kQR95-bKqwT^r`MJf#`EI{AKaYxJ zEL7NP!(F2Zu5hnE-^%mhXtKEAR*tV8IdN=vYkT$7iT2hmBC>+*z;xWuYSLRKDRexB zUqU=syNzC#+dF%mUUx7W-Mx1&X?F{Xx!B#`GZY+=a6Dmx!MbU?RbW1jNuqM&B?OEp zucerYenJ7ZcxDTidAqQ*jQc*AU`aQVOq}V?Er2MWBtq7qH-*DReXD62I901yC4L_t)}0bU+6c2=+r%W@^1)*>aeUK=w)yHKt@ zNR`m`cX#jIz1t#5#!-a~)}b<`VF@Q|ci9wNW6;b4fdzQ(pg9u5#t z69YdbXk?qf4K2)FNwsZBTZ|{P#j|sypJvW%a_ZEH`T2eec7FmV%iO)a(eI}3zWwHN zAG0b6oU zA=w1&1B%ln>m^5vi~)@yPXL&P!yPdtU>kTUm@(id^wy!&o+Q1LuCPfst<0AhEkYmI zI4xm(s4I#(l|vBr3_O>zCz+*0@yJAXZq z4~!len1X#ba8&@wQ^5qwwvmDvRhzJ}N&M#+@Dh2EqacpB?u}3sTk;av2@>(ZrEqw8 zs;Ypfsg^WasK~TMIBdgEh2b9jYr($TJVibZ!N7Xl4~ja0O${2WC@dMOorB*2vm~|! zsHA1fbw`VL;tTIax}D@=P@AhR^y-y7}io;!E0(`v8ZUPF!-fd(eYknqVAH4t4t zaOEv$Os<&XS>&)*`UxsyS{2Vx75YU+DPe^W)OZGE^$LPLvblxd+Z%AS@F=EWq_rdM zDtA&M49w-ezrWkcPz3-KhQfr0RHoR>KrL~O=!0d2k3mK+B4aJVidnVUYGQCex)FER zq-C-pH#LTJF<8sM_dOrpPq|+{i^7SpAo_@gA+5p~2y6tWVqI2^B1ZCw+1lL0kbxpu zT|Lrnp#_!jhbQ|~>Wa(-a}{I!2h@;r7pIb(MZ{6|Pq8Y=ZX9GG zBjgr5E45C_2h&a!fWwK4Q=(v6v``0axCq;ZD7~zVRnfUTm`>I?x_oqLaRnGKxVXE! zyR#P(v-y|_&qj?u4LXVNAT*bIPDy7G$*6LiW&v1mGKC)kl50);#7)qwU`<0Y>j<~9 z*NzQ-0pTdmKJ=NEu!GH-Wk=SXqycLP({_L;s1R1ESk+C?vA#03E6vD?vbOe$xSFm16;?%`g9Lb@C z;i_6X{J~>jlQ=Tvlykd?jbnlMX438tVJ<5xE4+`3i;MGUv|r$ubM}8@6^7X8-Rp|&B25A{MX%}X==t;KAA0mNaOeN_zyHra{_&4H-Sn}?9y1ri63M_s6UVzx z^_BvLL4&r6-}BKS!c#nqK;qvnGH@@*L+}Vj)IJN*{_MiRPpKWYxeenyw z0<+uN+CeefSW(Q++Nlqz5qcmzK)JZBqz{OjUW7!0=#~a@zW6DmAxw)=FvCVY!s>mr znrh}S+ z)Kil)RZ0TWdiK6_{xs3g6R)VU?Nbi|GCx#8CQCypRL;DJ(Z5OusJ>|7{7{HTOR%=; zAYJmwMB1CC`hhTCl?L($>_amDph&RFY`EhSlZ* zfs{18osiYk5|hITg0+m{!G_nJ~S z7bsv**`=HZgolBDhUn#bM1~L=G{z2xXV0Dmh7eOH-n|D*%bRb$%?Zy1;9blTCu=Th zD9!6?jiGu`Wv`vng-h&ox1^xs4OKoXJ=Fe=bIKA-moq^_lAB~yKaEi;FmgCa$4+~g zya~0bKBnNE#zcmlCG&64enb_ZC1oM@gmz|o0N*1>Gmv3Qon|Ao4%C>Rbv{}bt-MJ3 zsnmP7E_7(Z%JD49U(3bQOQZ-@>2^A^u?fPODYo&cEm4|v>&G@a;&X@_m1^_OE2T&X zvWZDVB3uPp6(`K_1)CLPeGQAdsNdxPB8nowatNl(=xAazn#T-KIY^NSWva8BJql|w z67YqfdDdr*(V$0~U|_^kv|6_adJ-z=ioRimjgHx5yCCo_(A1ewSu}}_-{qwBk4~GeO3&^G6%ArP4Wq_*(RHkU`26JrW#d53+$0u=_6F=BO- z++#X!Uoe|!IOl|+3X8+xcwv4C7@g&XMIh>TxHu5Ao8Dfz`rc@qgOL2x#i#SUp7z{U zl^QlSIVqK`@Lqorq^z;_Okp^ZOwCv%Dm5rMJC&WoP+^hJoO_tFp1?&A7lG=441DR* zC9Hw5uyFOg_u!rrCr-es!moyGS)8GlSfWrN3>6j`60=sT9sP*BxIpu)F?+M`a#ous zpM3J4{FDFWfBf(M`J+#q_=~^z3plR8AAkJW=U#mA#l`vgqeqXz)*H&!t~4x;!%b;3 zC!DT~TtZkB#Ec9D=NdP7@*g|@IC`xV?zeyYH^2Hnv_hzf56)=?IU~6==%raf3OJt}IA`Fm<8&PFGp6nMuuLB?MSer>eA8%z%6Q2T0 zK3FECl1GrWW%(tB2C z3Sfu+T=&<0{flt!Ui{iO^TA+$v+5E#718du5BJ$46Pzi^q9^(| z%kKM7@537v)hzUgF>O-1RhMq73HhbO>JPYBAsEG3d7UAkg-y?kF>dYdV0U*knHaIQ zY7o{sG62$|%Ei=#TjqnNE>cbU)k3Uvr5~@0BGbC6J^Mhdem|vAK-a{Sd1z!tY*oh> zzpx}y<_(b*ab?&ocgYAXh^f1~yOer;xU{s8#L7k^O5M+OVPtn?uT4yaDE2=s^lJVj zLQX0!(>4YeYB5=?zTTD9h6L)QIGKrH&rk6^^sIBLWD(22aE<_j!LjO-e9z2ALPZBS z=Nw!C%)<-}yRDr(c@kFR!qb;tef8BFH`cg*g!a`BbT^*6qF@sjkB5D@GWHI{2YoK; zfEd9Zq72ycSwemeLZiW2M1aR;;XwGN+)LqDWNI)aQm`^~V-1J2SzCr&ss*jL2O;M( z9}nkWDNCBKQ-EbeTN7_%1gCG;HPAl9M$%D(U1n*$u`uksr*$M@Mqv?13u4NIVO(d@ z)k}O$7l7$X8RL{xqIuc2!|pU%*EPj}fMZMP5LP1A!U#3rskcLR4TMgzQ<1GN^sfn_ zZ*HQAgh9Z7z|O^miH?$u^|WOX!pgwPIZG6@cB}KHWm5OX=4DiJ1Fk7Gg^k*(!yg0wO0HSYB?rk}FEH527ibaXYHV(K9 z#42aXwdML8MS*#?L593=;lfi-J@thzeBtut%h3OPugj*zD_5>Shwy!Kdlxe{_xjI1 z`|Kw_`N@nzi_nd+W0MT; zCuW^_!OSKS9olXoUk+64`0?Xs&YsxV*tmY<-S7PEPrm%+F9TG-o$xt7hiTH_wnSOx z`8$(37+$x>WHJqWnObe0SBgn@7C?%g@Aa==zYf=1t*n>;;b5(~xqJ66QROyB3rALu zv39vhNAwB@=MM3Ri3frHELrLZ*c$&&AwvXyWc#&cZAQJ_0=nLZ0s@@=hckJyU;w{k z!V<&4T=E&NlC#|(3}Adu4PXvQH@#{#z06cK&8%*TnkSOxz$&eQ=AwQvVjf1Nx6g!( zJC!T3O<%MoCO=Hm%&R~iL3ywM01yC4L_t)MB_WPv5z%xZF?O^jsY!0ejY z#8+A2n`)+>;i>vdjfnMCac{6L5QQva1n#(8?JYf8@zSNpP&Me0w_4rhMN||1Z zuL;dc>K>utiv-B<6aaunqX}1u2Q&`I7P+O6GY@fOnogNQ%$*l*)8HShOR-*zERv7a zkF`RL=XD4Ce2y2fN zfoSD~n4Ixs$f2s5)%0cTZsl0jzKFGh{tOJT3?h;({ssm~DW`O^YVM3yjk%rPcovzRnK;VC(Q>0;{Uk(OmkLE0Cr7B3 zhEHcGSe6XzUiZT}r9-?N=dNTN!z;rDOR`ktRZ9V2mUEst*7f3dI!Tz%*#)&Ouc1TZ zn`?QD22K(V6eI%<*;El6N}2EbRi~E=(I((e1rS znst|!S3B)nn0(lqTkCgWSFgNxZ7`bj<`&Xc52P31mRm`CXJ-#qqeBdbM_=V$yVa%P zk`2GWq~9Q4poanJD_Qd@!X%?S%r>7I%tOT42mF}SnwI@U2p~E;Tbm%Ew~};7Zvk$v z$n%8Fbub^2Ot9p`{(f(6j+d<9nnsaoxhNsb+?GSz0h%n-eVd3?QhP8_(Z4(}ARC(- z_t1QVnP{^4`FTv@&4wzvjmgYhe_=Qr?hep4n|P%gBEbx+y`%wA!k2EZ05w6%zRjje zAWlG&J9BfLx%s(;et&+nyLWegnD6e7vjwwq>?CxsvAKKc(xv%6syqO?V4Z1fARl7d z>Le>%og1LF4Qyp)>F|fV=w!$W+`D(r(g5JuyFPLJkSXVbL1HxoGK%Kpls1G3K7_t$plB6VloWQbDOXQ zn7##W)l^i0_nAmZgQBKdGsg!2n^nG)q6?q3dVZRLUH8n=uQqf<(JQ5;;4n5aUNJ!_ zl%h7GSMD^b+pC@zCfwtTs&2y9uT<>$w*1b>T*5=G5sDwp-Q{|+t)4jy3X3QF?8pWk zg2fZ8P{uneqCScJ<)7tJb8`Na0^(x8*X}Mb zVk7n(F35F?WIu#<7Xwx5!{U18F~VGo(gHIgJFvu2B?l9czeJ8GrFSLoP@m(F1dD@m zz+wqGJhM*RPpk~&f+Gc2(>0NQ;s{t&J`pP6 zmk1MI+Z3zp_IjMMWn>3#+I+%3lBiz-UI+m8<%{BZlKxDitMZMt>w;YBK;&L78A@%48d_Rfnsl(D-SOkcLD1c}xBlXbFFyS6xjT3649UHD zcXuE5{piu7r%s)M9=5i&0Pka!+Aih_UYNJ+2}Au;C~1%?LY_mt>{ZHL*&Rm8%y@BX zVzw~DukbqAzBE=)gL_~k*RNm4Y}Gy-4e6?Ra&0tpJg6wEd(h*reb-D6H-6V}G?wWz zn7#Stn;c||VwFvf9Xr;W>%Z~F8;gsJKw#kW;fEiF1z)Fn7_d`=edKI9yF2)zyvSqg z^yiTDX5{wVMwJB9Dt1A%Wc-KiW6vdkjX5*-#V>x**zuqL`Jcc1^2?jocfXN+1N!fG z+vm=md;008IntZw!d^ev|LoO}?IY7@!KDJ>Ps(Bqe84^s(O!Q<^%C<0T@R3=!W-Xx z_g#?o7nfJkv`j%i?LgfJ_tv(OL1?Pubn_`6ah;8c9xxvpH9R{pAv{AGbxRIVY!hx7 zeVS-n4_Y6AjVd=&BV;8;6Kbf(Uz@C?f9F3VpIv5E)H5}4o2sJNlKe0whxe8d4VNB-nb{^XfU&ph|sb3gsN z@57zIxx)A1WN&S4?cVw(NYV2P-B7GJT4RFtnDp);jx9ndStLu>39ad_OTV!SS76h9 zeUTGwNmR3oOH{wYAUYb3fDAqV{PQr+t2fqwF7UD^F?}wo1M)-ZG(V8m^j@(IR|1VF zYA_?GruGPfknlxDk;w49!bl*#VtYPCyF`IGzUP2*$#S4;sPf}W>*A;_4YTA*<12!O zRkuxjN_rE)*oFkrm3w6TzTsItYn-z#ayn>M?xYc=^9{_=iKDoWsheszQ-%~*os^H1 zrINpMbQ0IMpAb%t1+h5ab(vM9)@nRqlRC(E%{SU80M~%r$LbQojS%-0lqR(vGzF~C z@u;SEG4#ojkPnkxUtfnSz@Gp|0es*`KY9^kJwmAq53pAlPr>Io*AcMMS4GCdL-4Ut za*e!TiyO{p0$dE*oU@Kmr{;i7XC*-JaP~8mKI$30`sJUQcj?~lsFNW7l#%|)gp@xX zAS8Dj9EI-hT%Rxr%5U0Q&l&ter*veM{|}RO*D=(kalsuhL?|mbh{G!LwlRA3o{Q5k zEs^^}QUtx7agrrFRRpIv{xif;(5Sd0Ja!Su%yj4W(&u4hdOA-DIFe1+h8hbLTKP z(XrV)$fRWDz!#;7*V2onV`XE^eS-Ol3r;^wRNuy^Y+v<4?DtTCN^jg)JAeNCiQ}hmf@n6R$U;gP;3=^^8r5^mJLuW&0{0*T zg~8{6OTzlp2pcKpAVv|6(@5-YZU5kVFI~TJ4R|=@Zzz$)cwB`1oC)ljA5Mn7`QFuQ zm(QL%4UC;QtBV7CNz8aq>WZ1Bj1VTnE6sgvL+jjdsBRbk3mtk6twb2NffaV)I3TOa zd99&CEaQ~eTX$}EHrqF^-$*}^Fphyo_I3v=iz`d>OIXu_9Ew=WkQbOYYc!moQ?w(2 zBqc}URu&CeL0yv2sT_{>+ntP~`?j}tTdmIV6Q{oPrGNUTfBMhP{_@!u|J^tK`rrIt zPo95bZ!m)GpU3E*e!GRGdWQpa@oKj_@Fzy?lB6190Yl0q_MWAHVLJ9e1r0gaf9g}8 z`u_L7k4Afxih)HKx!pR^g!Zg2R(+xQd_X{v0Z9vl6fv4S>w2 z9_I{z3SepqWbfOI4=K1Hv2xz)I@y|7EAoRtU1Skll-=&{ZeS_Pno%f7WVxD($Hkm; zwd?X0r}DjLvkEW)zGAK%~V-sNYrC)a)AeHikaf`mNf-z&mKdD ze3S@j5>JFShlwlFR+i*r6G{)D=@%3GbJ1CH7NXh_lt;8^#2*>vL->l(e3K6a7@FIG zsI}Ye1G&J8ZdJPq+x@KS@nDCCsZ20^&y$$L(iO?h{s1nFF}*X&OB-987*cWkn7?tI zsu-Xj^gsNye{}Wom7l-zdaJbvGV?Rfe|&pyZ~fNBXyo?>`xbrR{oGtHrSieyEaQ1G zFV&R4~k12sjyEM#DKuVnW_?#?=mpKD_ahIB-*m%o3Pq6;*VCMOkHgYZpky#>QrJ zX)!^xu-t!H0eH&jBNDx@v>DE0mF8&I000mGNkl5}!+CZ5#HKNQu&R;ao_JiV6hJe2Zb$-2@y? z`3v}^!~+C(-y|gB31Kz?ECX@!rbhLQ_qKwAkZ(sOwD1)R6D?cNR~Z{n6@3((?KxKB zwUi1c*tWws%UKfZpCH?hUfk%Y1AN7V6z+%>hr|8haBFAhoy(U`o;-Q>>{;LpVeXeN zUmlD{fMM>g-=kp3O2yY8*Z4?)3Ut)X5t~^lK#haNWH70jM#A*AMrx%Xa4H!1DsY;H zU=*i~dqWdMVWypMzC=nMo0HusNhQsUAU+bnSbCx0I`0yd`o##m#8X$JUV=ueij8nS zYF=B1QPWPDesq(owK@y?Anh=$$@^=Lo3re z$Hwju+|n#%qlb^_UU?+#tV9j+7E)($$$MMl@M^4HP<%|Adqsm0|E58P3e1OJc3agv z)gITFrOB#tt65PvVP+a?u`+@vZ*D@St?I7oo)li&1S&MY9KTAU#>{B$a&oV0aiBhk zg&;Xl{AWlM3|tq#h%;}Sq+EYakq;sxM|6ORovyOyk}0Gfl2WIxC9)B8Sn1y&dtqP)}As^;T2%?9wP37WNn@B!=4l}{5*2!+uLKQ4Tuor&0tW#7PF07V!XLSXJWp? zsx&AsZHhxOl0Yo{VU>21V+PEnPU@q6oHMx+fG1tW&`I z;V#=)QvFo(S-t{Ck59cEC=Kw<4owu5#XPQQP3Be4WXkl*KZUQCFIqOP$iuRVhco*OKoOEkB1ee{375R&IvYk0mSx9uBQ((f(yyI56@ zvMyRq^1+D;JVv&*fyKe^bcv0QIXmByDv#ni1D@kkl?5{3{0vkllZl%bMc;rkS?j{( z8x!>qcN_8J17bH9V}`8>wkf_|w?r5YKMGPj+7gZN2QMn4jDYHAskiHh&v9MCkV-Kj z&m$_C>{YmoUZCs1bQiA${qGXR00O$vZ6l$j_e78WD5zL<s#O-5$BAz=_bfyCQS&|XOY)#R%g?kL6DHjbFGGO+a689hG z3hMjry%!~zjrp<2BLqv^Vy)&RLp0^g1VA)lDWWd&=~0!6Em0cIkdT?dHPf1O811ya zDd_6&Hb&sj>P_s!CJI;Rv%!cL*N1yc;=0XjHJMpH4|wDkZ=x#?^eDcKq);jnMl}qg z&_6@ukf`Gsl1%+in+O|c6g~k7jfF|^#rQy)f^d8Dx)6XZlfcE2sX72 zeXJnBdu_{lunKN{nZ=q_Z~4Sc#svr@J3Eunko%DiA3%~6HBlT(MFvh(fg;&JvANia zPbYJf<;_am4V}wvBKnqDYlzurWdDH}o78FuVh@uQ2bN0S0R`vsAQM~pDV1#Ao|s>U z&)Ya`Zb_;!r*5TbM9!K<(Y1?Fl@^Rox+CV&qvjJM|Mgo)x*=s&g(whz?uDcpJ@=h(_vi} zs}GU~b>XXGx$sVnrPIg<1@#L1J>{D`*6gWlxN5g=-@cP?uCA^wb$g)`Vsv;MS`|?n zjcs7esYt;XW2cRxcD(hoQ;}DVrLeOT7#gFpaH-Cl?fq#7Kd3f!REOsqLP1WF0$WMY z@tDT?>pkL#)}|&qp{xeN5^-n^5Oq%MfzJKJ-HNF}_lp3$8)m zMANq;59F%JLiAWXvBP&hHL1SN_hKW_U;$C$vR}PpV?t)UhcOht=tqH@O+SWW|EN-l$b_wL>6*RQXwt&N8RvHQ&}%s=$dLx3D%3;+-F^Yh0} zoMek1u?q=V6f?2_mu#qy0k<0b1YiQENQw2>+Q2Zjy}kX-Z+>&_CLpBSr%s)+TS(_G?eNaM8Gf#Y=nK}KVc%U7pG63 zhW+)WhAZ3_Qe@i}sUyi}i+zeza=u_vjsmbD3kfd{XXt@F1t{Lz+Z&IDmo8m;>WTB~ z>+35kOJD!`*J0UVb92bp8cKQ`5mBz zqru?4_uhjqz=Hqa@BWVCggf1QJVcJ??%gd6^EMt{m!>TifC+Bd#8E1S-Rx>fvh1?6 zq*JTwBa9-e6{=Y^UFtjetBd6#!rleE6m<6VEZX86hA?IAcIH$zpeYOWfV5_+G$J^P z*Su+Scu>jH>v#dR2$V5fog?Mvuf^TkNzuryc@U&M&$!1Bl+vb8C=I#2N8g;1s zw5^2Q@AY~B36jeG18Ge<4o8x59Zfh0oae~)K(^1oX$3|V4*t^85_@x;J9iEcJ8RaC z967=n98hcmw9q0;FJX@Hq)d`u6r~+lT%a3FofX{fU76}43JSbv8tF~ng1{M8f2 zm=w^Uy#XS2o_?>JX0e&1l6kvMmk)R7ti7MdZEQ`Jwf5>7`(ESkYu9W2L~CAJ>x~a7 z6^yZR9bjNE;KIKcPT33q)~#ywt;(WmNK>a=HKB^(k-)>GJY8wy9dHgw{G29SvktiFFMxxfVbFK*oDW>&ziWZvJsk=&01Jr z(~{WAM#r1(F95rpoh?6}V6j6!TH#=@HID`EgrlMX%V*uppq(vtPw|}mdS42W6G~OlMZj0-23!{ep6iGZz zWsG!GD3;ik9zmj(&{FVEAgrP+?QFZ<0a125+8eoIb#(;+I%#1jX_}>-me?G$6E&lT zloqZa$R_qZ2|D0}C?A{T$h7Oogld(^E{SMCb5}He{8x~XIp~Qk@0UJcI(m?Mp|Yr? z-zG~feI)D(BcgL6|6C+|lpB_VSaH0$D<(xwTp;ODI1vJk!BKYX8d_203jY#h7Zr4t zSG&nFmW^|6Q|3%ZF_s{9chc@)G|n--vN?MEn9b7O{M^ zNW#0ogLv1X9KRSrU0}F237oi4S%+erDE*apAyX@3MqyAwb}nzm!%?S?W#xQ9G48}{ zF>}`KVD9f;ua8;v3re`dZk80d$wEHN0ET2K`^(+UdoYXnUZ3AWD7ch?MXhccOnGhN z^p!-#7Z@e13XK$*w#KVT`myGVOckw(Y`il>H}YF|ZlhPZD>|?>qlpv-Flr4Qsx=C0 zIru*z+{?qD^AgP5jKe2s;#!$cMRl81000mGNklo8yg$&D-gEp*RNl^coA?58?xBqWZAJWDeVsxuw|W*b09Z+(phkQy(va%D?-&xHs+vrM&c(t7(765Sn`R(-1;WTN2qNtQcqD5g*c*D z*2>3NfQBScTT(%@nlkEp(DFku2*KZ>Vr#0e&(!Jrh9bZzJ&`cnma4ed&d#iU4p2sa z7_BB_$QUw2c9f|V!^|>HYCRf_0q>a@?`?u$#;n2vjG2yCMPuSA9X;?x&>>nWDQV*2 zIsRtT&uX3F;`s=UXym<>1oVjNsYRyioWj}pI4b7U6l7oNs z&FV+S1OsnX)+qa&B6ZVuF26*Aw@;%v#QPwM>yhZ51EbgI^L^~6=rm;RG6wXBlMX}9 z2QQXSq4EmySx)1T+sMF%I=WMieDpU-lBCqcdW|7NRHM8Ci;tksi zgsYt8S|59>;1>Fyl@%c8`2vfclqRl{{fLi*kcWkZC06$3z_Jt*0&*h)BMDx_t7|&Q z{ z)Hl2A^MF5PR64%DVk-#ath|fF$PyI7T;%V{+v?=u18lN-wB~Mpetvs<`^JqM=gvM# z+L5{zIq=qb!4*!1!yz+3ST`j`A5A>~G6g*s&Az*k1f>K=3U3Q0VvZW+r#P#PQ3}oo zji`Rk9ji7fp)a0RT((%d_DK&iFs&gINk)*)`)Hb+Jjf&EF+*lg7APj{QyXSuy@9q3~=@HpZ^@QgU({F+(nBout}|Xk>x^#Rya_kMAp4ze5|hMeMvXC75=Y`InjmAUw4~Ow#rTleKp(CHZj+6cC~nvS zHsdTVE_S<_RKcylWUxsVHOSE%s>LwAz(27Q$2fPKp~|Wnl2{F8l05wI!;hRhd*Z~2 zuYK)nSFc|C>Q}!CBI~hZ$6!5=9XU$g2k2J^cm|%$(nPe>i3(dvqO%jK9tfww{qP{y zQ8;qs2uRd7*4F;&EB|J3xx-@Z!op}W8o{qH0QmLUXPlL2D+Aw_8EIf7O|9)F_WlCTO3EL=rH!q-%*-Z~v%w}sM z3KKQyH6+7!NKCX&A-M9$2g^MWB{G~IpY!CKDjUXeze`I?DMk4LCIPV=4kV{$WoV>= zx?`S&Y&zqsV7g)DnypxLjZzOOf56f{<70U?eW$EgSQ9mu2j#4udg`gCpMH96eQSSv zorlUb&(pLVB=2|Xw(su1WHh?BCMRH{d}0GvU15^tPGMA%s(&>-V70A` zt3dNElN;2qCId7@0v{ccSp==6#ZuI;VOZnq6gX0ftiJxeDQ3rM;t!n00{DWFjaP~y;R<-2W+dRz>fISKU*NRnO#>kCYJ(-1mP|%S)!S@ug2rzAsEefp> zHtOc`O8^fILX9;8fb5J11?IHG3UU~nl#}1M;TTjKI2$A(Xw^$F@o4F2$2o(sTNVk5 zh#U>&2}XT9S&Oac^*CYK42BXf`lv#ngHM%jjZnB)8_+}@gFTFZ6j@Yk)q7Naovdk zZD8EFDjgx-td$Ig#bAh*z%1diL%1@7y`AgVZ~pw}uLA7t5610IKTTW1;TQ(Kw6roF z<#YW7c>LbR7CWVL1R87$h$%FE8^`hO#(tg-;*SnBsz= z8wEL*HKDgjs}3eDNr*z3QdCLAhN3}#2i^X+JnOE{5 zT~k4kv4)%<9qZRQ8M|kPVXkVPSXNMDHsmA$rX2Qb$3#g!YN^H;TIHuB81z zL)Ynm;JtSH_S)Lo*|TSV>mUF6?(Xi3FTQx^&K;QcBab}%_S;vk-(3IEPkxfNS}(lt z0u1%1KmF;?fBrM4a{L&>*++tXNo32U5rgNWb)_caHa9|8Qc=nzF@jev@*_g~IX62C z34BId_j@n^*KQ}RR*F-Ixi@Rf@xd@AUd_#)YCMqM1ud27J0Dco z2nibKUu|vw|I)OyhKm`+3Tu-G(x%ShQbKo;S~2wmJlyGY_;iHr_z=wDh@vT0g2HeR z8$>rneD7p1Sv}a`|%F%G%vd zzuzU5v?E4!g5Fz&OJW{%PBdZz7s{CQJ`2kj!!`!2rJbe>?4zN`D5$HG`1p9h1J!e? zzl$MJcNh>IDVjY8CIHDE3?^eB8C!SPw}5`;Ir%?_Vb^6s5eTP*=(z+XAtybUDWH))lXD%UD8V`#E#nDt5hLbeVjPz!! z3J-mQwx@}uy2+S6Fdy(?HW?uxGK`Dsplj3Bt5*|CRRmKiX2ZJ}w_oEC;FZ}pIU*}c zaMg%;J~a;YRTofcOw2^)OsZ*DFiLPTJbLsfoBIR=n-*Ysq(FCFOf8JS!|5^NOz~Zg zakulzupp>}aiSpsTMmO_Lmy1h)!cn_+o18ren|1jtF4 zwf~`fVG$VrBOOFR>7amDOQ^as0gZ!xZm-<{nS|rVpmPv}_V>0aO=w0^=mf6p>|kDK z1_s7K9Jk5riz`b;qtm>JqF|UlmwgK`qi~sZ5cQLwbs-)ass)N{HHize<{aRyC!!UuAaBFluU)$W z7xy+MriE2TLG&eKQ7+*q&_D|hOkGlp@3B^I!L1-3*LY7 zxY`!pgVJxOL!wBMk8=?C+nl2t>m?m3q0TJYGz%Iv)af4NPYu{Edb%Ex{N49X ztJRVJVKiDMX3PmV3nys>WDS#PuKUe?rZOHTo?KQVTG7QToWKXI768 z!~wu;vXWuI+kqAUuFl63tRFrYaE3zGS|TQok;8C*isFmQ~V@5tO81 zw>H$Y_>iE~s!UfhetqbgfK)k~G0h5Jsad*el)}XIp`Dh?}NN!&+_`yIb%T!Eu zGKQK&-E5lG_fapo0CFSK5JqD2}*vN!UHcl;oLbn*?1OA*}M% z2^EGlT-PzGdg4+WZ2_~aI+Q-GV)Zn!H%f(Is*qtTkFz|_yHW;=hm9$w=d*n5GIB|UtFWm>LdS{1269W0kaYB4qD#`g3hK{kWUblQZ6U3H{JzV zWq&-`-XF}(_ekq9A$W@6om{Pqdjn>`000mGNklx2~O}|k)u~F@u&g8WfYSTGF{tJo2w&%!ya)g2Y!i}{pfgN z4(Fhe3VagbZ^~PZ33KQv8wv|c%MEPE7-h!9aXxdKW3>~HcK&E5G~?F!ssWSKoNOzcAm%oXlxX#}J6h(()n+ z!+tylK?U|M%_!2?5JvD(-9TeYD8KiR66cJlvQhy^Bp+cyksH@OfVrkVIn!y&BVO_R^>RZHGwu))jZSk5^yrZjkS4GQmoXY(>XZKD6+vT z35#sWc^KCG-qzOMV9@XPdDu0TlV1FQ2^n~89z10vBLgFuyx6$2zP*PL-Gzs@P$@OG zM0n4M%?Fe5&c@vfmp%#-_<#CeeCa#i`Of!$_>-4kedY3%cRu&I&mBE_^wOnEH`ZgbbF%-W?0nemcG&6qd*AyG02RRSQ%`;LSAOMJu3WhS zpMUTNe{lBfsc(G!d(S-gBy@G}-o3y4%fGyFSB@A9J)kNA@oj%QLNB zVoW8kj7@k|#Zc*!vh=&0N*8%7;jqJAkh^RuJP;quENzP>j!{WLwNiswqiA9NbpvP3 zfzWHoKb$4G}fv< zIQ2^$Zt0`QE<%#3gCQiSd(dp)N=;4Zs4g$vuT4z=Zd*VR_P4jT?g0WvXeY-htoCcz zFUfV=Eeh{%b=w_OHYM54?mpt&G2BdrE|KO>OiHLSqo8#PWbu{)Snwa_6-X&`UUWdL zazk?%9e7$hDhkLj>)J#b$-Ry%P=sJnuK+{vpNS!kJV$zz%(X6*_TXfD7&7XT*6z;E zvE!#PHQ?EETqRgVG(wKt3|M*6O4KN?rraY@c<5l zNml4bZ;B7qo2E$GJO)5eq@2Y}$l7@0)#J+28=k7oPF*RbveFOHC$Yw7qVwT1nh`aN zCdUd4nuom!8{zsat-D;ejjGf}flU*)1P`gemnQn=NIj=ONW7qwFD7V|;9Ro)#e`&R zm~_DLzLWEm@FS&s=XJQ5OoSw=87HNAQCK)Q?3{!ZI0X0v4FA?!Zw&?miUk<-dwok* zG?A`p6AQ6SA8;Ik(43fp?I-xw4nZ@qkgRBTq+?56tLepVqn^9T*-vc*Pg5?=q&@PM z!=LHduU4IFG&BWRYplZu+hi_mzZE{um?Mu9U?I zVdkU~gNtQRDuS6Quf$K@ui#inb)kc*xKw;3Wdxvp9OPyMz9_FAuxNoV3yzCi zjjLz?v;dQ|eQy&U+1cJirR?4wd)DFGgLeQ97z7>=W>T^+ura|VjhV(J<-c953G9O= z71uDwvRhc}oaF=iApb1e4r6&Rq1*wU{ zO{EfjFdkNKW*Ek8MbkC9*Ykdh3Uhk89~S4j7LB1J&aEoCv`1 z39Ko+1h&smNdjgtoX?rfxOHnYFUoP&20T@gx538i*)=Iq&dF6uUg=6ktNUz{de35x zax4;p?yCWM)=rmN1w9@h0Zn~mYC9NvYmob3v5mCyh|zae<%s#$M=sMSnq}14*MzJ_ zTlHH!DT!*Qpw{3gfFi&Kk3II-v17+zn?CW0Prv~HbO$`-)hq7-D+qj}X6GvKQw3w) zFsB?Aef7y;AM03Pd|)@Tm_Lzt4w$eHx;svL;~jeJvC4)mG?t6Ic%>&+5`WPC@%iM) zJucl5GBI%e(o!)dq!@1?u`1kYV*UWqO3F{oXwcY0>Vr9!t6Nz|raCmE;-z|+d(?ce zp&z?WgI~S&k3WP3n8I2sw&Kdq^`{CXnF*ONl4x^i6V8h!ZrB7)>}!&&)tT!roIHIN zM$Y;VKs1vA{qZ~9esE2+DQScw%2ta)e+h^rgf1N;HP-8}(ko5ac9D>O0S84mwC7n) z6IrHeFfp>)TG1_qP9&*JFqoQPIR-(V2msB@PRA5XbOEnY^22c>z+q-9&zrg^{*z5S z!omX{YzIP${$#`aY zQaoSr6qo!oENEU>tSTBRF~k3Yvfue`tNr@rS67yn{^g(l`R%n^hG-;m@HrKCVfX6D zg3BkbTh>Bl+{u$Cfz7>e;R0NF`st@RFFN_Kq{1P!=*~dcyy4tMckbNT+1vseELy)L zRul07SPz>Vwh324J`X_XnsVEirw0bJv9SRN9fl5qXp0&qEW_Y@LP>NGoYLcl9vqbe zq5h(ClD9=tjO}P2_+~WNW;te&ZCe($Cz#Cv?J%BmH?kijNZ!X!o_y}P=U`?2?uXxp z1`G99|N5(Ee()op3s0VZ0)BeqjW=MyVKK4jQHcEuG5Hh&h~M9!2Hel*KKD5QW&pIk zy#YMJr3By#e1ZV{$AA3C(8;SWzjOT5671d0_cla>%=-oK0Avrq)yC{@Nr*=%=^S5) zi&-*@kzc8=eB_nm-P9AoK%fZXg~(^YM@<}xyGfZT)X;cf{N&fy0aTe~ZM2;hZZMi) z^1!yiZ03mJ3Gz#~sKBf@6Y0s21Tc&~O*D)whGxjXj7qQ4&W}!R1qHTw z`b_n+Q~7@FQvUC^h2hZ$$B?%Y#63B)3_<0=(q5@}Vse(Kj4aY*UgBO$+)Mc`R=2@c z!|7mye;`0i)DrUb{~#Js_6b|&QQ60aPYf#w{s^5G7RH+AcTC(laUVrh_Lyy3`eA)&AosqsbX#lh_#LJ-2YBJ$61|xs3^Fmvhlt&VsX4e zfW6WfUW%KuNRJkhr@s}wU%ik?kaU)pm*=Um<`=kP7zT*G-A;c%ZHz4!WlAai3OI@W zJiasI;&sJ%ANY)|tt}W?ztbo8r!aH*tkLF@y<_=OqrBN`H+4nix@HP%2t{L8%|1@; zM}6vNy=;}OjHLNV1F%~3{ZN`yQMimXh~)~BD&IptsgyHC0pyl*5drrPd&d^AR#K*7 z7gMchR!n2r<#^YwyO=Ig)<1MoFwrdzSb5nO0gtISi?xamQldg)d@MW0tfzaw3`CQg znbj&FO_OCyyBNR|iAIiRyMzr}!jchbHqNo4f!1Fe0qwjg%(WXgKL7d8 zZ|?445gOA9MyI&8SrqWNH789jy3 zTUlN}2|OQafT1-hkDI*IDt#6=AE}L$Z-K@+%t7S4eEIV7;?mmM8b~{#-Vdu|syK%` z6p(-sZf|eHsDSR8sJ;#BL*g78csY-8AX9nBAOedCXcT~XX=w@PPIeW-p5ylca)-u6 z6{%Q11>a#JfPq2aeC@T@ZZ9vt@WKm>^A17W&g||J%&;o0oO@y z4E8`#Fue+89KiZgckcq5vUh88_N0Z~>32~UWnrn??ZZ#4&K!zl8K$H6QSHs?;(>wy z@W7q0xg1N(_^n4NzBe~FftbPlYZ={D000mGNklyd>lyY7;rm+JXqu*3>~moqTaB zB>O>U_klM(Yn~&g#nw($v(Andb*A!aHMYc9BQVBS*!WM&$huLMd}>K(e$fd!%5ofB z5-4v)8c94%_Sn%?ARKV#?c2Adyp`z%xvhBxo=)wB*(%wtW=hr*7&e1y?;YkPY%G*rzhq`+lT&(g0~ zaj?w=(1M?i0Vc^dh?MPiMp|RXf^iUMNQXU{1R1zYVMX@XqeqXPJ$v@($`Lh%BJPx9 zY{Fm$C=1RD;C2dh+C!%V6AaEmd#w%O;6};D^3OyUfZEb&>vywhYw!VZK{mM(-H9s% z6CQzqnz*Yk)`-Xl(wb<>))@QhjKqWQeY{9|prooLmo5mzM3!R~9;mTxm02WHPGzA= zPnC$eN^}@R4!jcpl_wXtXk%?`wAMm1Ai;KnXp?5GyPI35 zP9NLa+3p|dBZ|-3n*JduV8Yxa2j&B~D4RMPD*gIUq@=7ZEi5Fioq-c$m^hF}y_Gt{ zWLiu3W~yUK+#YKdV+D2wdD66`F=3$13zEvvXezRk(ob;jHY1y3FdGrzQ*vi7Creg` zcP>%i@uvwRAZEm)T%+Dn-+NxA#HF=64`@+fAl)kIl(By*jl1lf5?$ALI9{-?B=HK+Q#yt&1~2 zKS?TeX%dw#n;R#buq2td$(T@pz=q@E%(3PwU#+}7p*Yz44bKF13@7uT@+zlKtR6kK z`pA<{T)%k(^IZaKm37m0i+w0~r#hWpLI=lVm?z1x3?AgGVhfX?XSdJM;LBJahFh@E zJK7(RC(@V`%kS^+?Cp25p z6emKWyO0u~qOd4=CerSEVzUzxWqdu3TZ+71$k5&M zbwaYUy#ut?5RfEU`q<+i`N#k9?*RH+Twa=6m}i!ET;xI*#m+`nJ1>GUrwoOQAl`FD zC6LOn4($gKZBgCg>8(a1SrG}c_?=s~;NLUPJi}TK;CtKc|ChNpjkP4X&cq^exy!q6 zt+&-)y|cSXk-c#zz>#2ZOnGRJErEhy1F~j*>z97}j{%Pi8yE<%{}}KO0fOWaI0M0w zH6{T`Ly43~lj2ZpHoM8L?&_-QT3%JXdh6YD37>Pmh{(vi_f=PQH)$uUFYmiIZ)Rk~ ziL;;YbR!E!SUEc))T}Dk3B+!BdkjqFhogC>fxkJQ?^AV(Y*jQ zLCU`JWD@}hIOn+E@2{_|(YMb&`z$FmBvgLzgC8929nna>|NZZy&kFtgnP;Abw}Qsd zAC92S(9e&@Y&KuMeEG{?{xT=0WEmpx#-{Qy0tzaex3{-{_jiBy)mLAo_piVH`rf_4 z`AeI0e!qVN1A~-2`t!4&{VXl_+i$;37l%7TRuwP|F|r9(IZ;6j4+>!dT9{ITFcC8P;`#(^5qxM1jxRD#P0|D%vx=3QD* zO{)&Q`;~b!H;&qPkPlZcbQiC*&x|>9G@fKSO5jaPbP^?LF*}#8`=ts@GEV@W9%iKv z=7cB&WfYNQAhVapVg7088wj6$NY6{$iP#jQtkJg0Co)c+^YNrlM#|dS8uElWFKo&_ zENwDVi0P|}JR1om>80D}HnOmoRn&WCZ<>iB`4H3g8?%3S&b2qcSj+XMG-e#`97)pBiR%c-Vp?9W%J7 zlr{iFio|0!C3(RHFpN^|Y|*eU!J`T>>8xCJT5?uj8Jg2>vs9)97<9M+w+Y%vv0Hu&uH6#cRuj#Nk`)> zGm|NeKSPtO3ep%PlQa=D{n|zIjLun?#{<5dJpmUE=%o6oQ#z}ULibi_%O4&gLkGOH zv5PUD+3ME^KgCI>8MhOSi*=Eq0kcd*v}GodZ_p527=<1%gCXAm_prRYOxh!TzPEcQ zw+RyXMSYn=UKXAqcwZfnO)P2t#*4*xZgfN53j@io|zm5nYB6`f> z!6JX|x#x)F$XYu(K0t=8aybha2{I$BytH7YvX8_7rk`wWZGny6xN(Dwx07fojP0Lv z&cj>IWm$Q(yiLyYAO<<2Jt*wV^9t_B%}=$m{(_#Oo%|q;x&PC*FVm+7gF~XIO+kAe z=VJ-&-j!9ZV(cjJhU3YIKjPG>Q)B=?|NQfx|NQ6Q`0*Pw+durlf85>O{qA>u`0a0h z`;}Kd^((*fD_Jpp>Zzy55~Y*x+_^&&c(i{&1oM@ze1)cqRQ5Ax&d^UtT!Ci5Qs_o> zJDO^GuFrhtGcUaG!j&smzV@}R(GU0c4;B_U?U_Ry6S61u-~avJ)5TApK26%y$3OmY z`kZWl{eAApMd#Dg(JhqkO0Bpl5h%?qQ)TsqW}Z@k%tm_{arV|cI8q$p<`&hwRRq8n zd&?R@c5{X*5gEMlj)u`b3|JhN_U^l3T+nb)-%zjnLso+ab35*2Jntcs) z1vTm)M1HA&fg}72umeBy?D(DxX*ZDyNPLx8$MNwoY47MQ$I>$ww>t7KG*@P(F@U

X{6D5IdRm}c{>`7(`M>&l8?$X zn-kK@$YZ_H1Kl;3#C%9iy@{pha!H|U1xc3amO?)D(bYDT=&Du~-CaPXsoP{nEIRfG z#sEuJe3VE$W3gVQKvci}kG?&DpfNC#(s*{;1 zs^HVwmDm7AJAqP_2)ziD1twsk4P}E9o~BusInIBxoSR(0)`lZ}tOPcyX?9)g%-j(4I)Q{tY-6B1dlujhs zE{Zi}g`@4cv#>WS)9hZDs$fOFaQ7?j!_5ZMMlw1mC<>uWDU&sg-0w<*jl41~%2JZ% zlg%a79v>Z1=}~>8)4GuBiikZ_x9Wir+)9=y^QBPK0ZD_JCis~7v055O}8qa zdYtf{Y&4pTdO&(JazEYG+?*Qa1Oa?gO)VUEHGx9uh^`xaW-29);>Dj6HdAWLHDM3a zk@D@0_I1*LPzl2yei=5fYY@68(JXhihZ&SOYAfpEu2KEr>@3uphYlV3w}1OLIGejB z4?ORA&l_1i4)=WJD_;RhZaDdr!NI|M?zso%cP`6NoU_hms8ys=gzdgwg4H zxB*2+nUgz*g~8qvDm*qZEn6hC)s7g)7jg<~e7BGX^t!DR+J@3rh9Xbg6C#gZ~HRsm?lyae|T084x zt8HLY*=W`|+mQ4M%~S<7&b5)`m@-gO6KuD<)RGQ!#~4N=k1qJR`GtXjfy&?zP-*q* z)xd(d&2m9t0r1e!5KO;Ot7Bq<3>jxZkR=BX|G)=60G#m9{`+A7?M@BeSn?(9*gPGO zBJAf%slY_$GA{UTrxo#TXNH42L3%b0EKHYOzLar8gYc(4kY)Yo9q6$wq1ZK(n%3)7 z^&{AiXt;`|AwJf`RE6W7TPX#y3f``)wB87?`(5GK)zb8R?Q!sFzebuBcUV#D5zH7| zZQ=~dxKQ!c9&L={MiggSeoK(6ufF=4Yp#K% zf9-2ui%w?Rkg#;ee-mA>cChHMbA*Z02nS#(>Bd7j(Lcn4Ky5ebm67}w%rK`VAZL&;`D>D5Kd3C_QnLga4~2&TrZJW>#faMvZ>=}5ha8G} zFVjNpnC-WyHy3-7QiX=Ptq%(jm(4Um!PhAfFe07I7RxiW<%~NZ7%o0Iq4J%ky3~by z{+P_slcsKQD<9$dnK$%Y|Je*$$1nd&x&E`w_m_PIV1iCgP85nh7?xAhM=>Wvz+O%} z_3C1yaq`ZsV0m^LwLqmwqgBc0!@LxIWuKa}H``IOx|o+`^dHBqg9q;0xNZBUO`DEP z&%h_O8o~?Zi-@olcknELwuDl-fGq@I@4}NuMuy=2Vu*HlYuk1ZLQ7Q)>D+$%t)TRP zK?`gMz7D)bUMlO5&NBxlTJS6pBMbBcKW|*QuM|;83&O z$(PEA&Wd%3%9kt)B}-Oje=LD)0u_H4h74HDvWMuTn6(kp@eq$!Nz_poxJw(iWb~#~ z7m+X@Ld0d$AXX8I28E$gD)vxX>Fl<6@gmj<#%YlA$sF|vP^!~vb0O2%*jPRcfx=wG zXiXqT*psiCOifrZ&f{X5V@0&aTQ;HNZl7hSxh{z}?k!AaIi(9>TU|~RwJtYB@x269 zric-GlgzqD<2i1l>25Q!N~IzxD9T6tEnTn#e{408G8Ds<+{%KJPkQn;5o|Z(8NMNAnZLfYgG@P}lmitz1_G&El>;iGOBrsJxOZs?|R@SZme_ zKCP^mSn;E@KqTnwl!0V2YgRdnE48{KEbgU}3~`i2trOCTLUtdZ9K~z_P(p;yJ`|r6 z2-@vl7HVUaBGSoRne&3#DC?kpF0=*!!%A}*f0QO{1JK`C1;oBYiNq}B<%KygZaty< zflp0MJ#=t#ety1MuaQ!PBVV^}9i!hRF4mV5?y#%F06YvD1k3?eyhH1on0_trOM@VP z7{y9Z#NLKAY+RR*27A*u={-$^GI`znG^@n94!zC``tI6YRBS zj9if#{c~T+$!}a4tZ-d3ob95V{5`Nn;g@EujYe#3nYBYqQ7#sNrGNP=p9kVR{<#;! z2^}3CeDL81CyzV~#Qfw}KC^!P`mLv(2GiVp(z+-8+If}!Q6yhX3cZI_!LTa%QgPRv zyU#uET(8|KRZ4z}{PWnvMBHq8MStDcShKN=D0&_&P#b%I(?!`yf`S|Z6HRiNsly&F zSY?nGsgrZKk{T{~tues=bkDwfzefcr#NjDS6gUo39jGD-D=!OX`uZRUCyQPgh=dC+ zxB&k7v5#LjHrDvT_iiZW@-QPHZ{I*aX9^(4Ly3&4s4dhKluHboigP%@a!Z`PyOs&? z9tL@F`st^`3EHt^4CE{bQ1~llUvGtPf!>cvSU}2l5TQpg!pb8$kG{~|@~l?G4qR&e z?X!zS8JIwRqxJW(o!>)nfmsqEXa3r`@GBVh&vjw2+Re%2APSMeD)e%y4xYYFoKi)7 zA0Hq1T@OQ~7W~q_C9_Wgl2DF=X|S(SMRbZZ?|avO>svsdHRJ0FQm*PR!#Q1^J_Z{} zBx!%KxUjTz?z!h)_nqr*xZ#G{QhoRC-JlA=@Par=qbMf{dAJh;2QO2V76xRiwWV4W zI0-uxzye8db9v;40CFJqPippIz%{OzfuuNQ7z>n^ zT&~3iErNLa9y2M<+_9NQ!T?F?b##0at~uSs6DWPj@;!ZCvWy9BjSG{Kt#y~!=GIA4 zn-Wh4e!Kio^u^S282&(?5&EQQ96EG@v@;!1rvp2o?i0;eC+l^(1=Rf@m~|2f(An%7v0Ir73YZ64PTu3Y`LAx^ z{U;p1<>4n98z1Dy8l_LWLkPdn5Knvs4?q0y$3On@;gJgL7;L{z$+e)eP_k`~aRT6c zftai<*WhQ7fELC_vFfJWH-HtDMN}?94TbY?zO{Y(c98VIj`!@@<6HKvQ%t%lH-rQ8z{)G;$q{4tB&6ng zIX|GsVyqP;HC6Uz<#vdV!ysJ@V`$< zLK}+IF%3RTRu4uMg!%w;n6cBL{_MVn9HTW>cCGF5vC&0zms~syI|uYg4y`b5CwGDG z369y{t&QhrI9L|LIfE-q6HSxUsfcp}JJ$B-eyr{?ABGx4J>cMsG@0lWzvXqO6h~I| zJkJ20v*u(TOFE^~S? zimg8vD_p)?Tj{9kwiu#fE!@F%&t&LYS-*X@bD!zK{>mMHgN4JNY10co5$5x+r z-gzgVif4pXI?LYCdq9K`WYmEuyyK3Ekr4sBi@9QI@@NtRF$FXM!tdCzW5b3G=bwK* z(3uC%p*g-SirN$}%Dg0`+;*Z?n+(y!Qd>KWH0L1_nT#rXl&o8UBb=FkL8JOhcC*?p z=$ysFr8o9blvkqX;+aU19veBM+Z3-Z7Ca6gadN&=S$z{_VPxhXKT41z56m%?bX1B1 zUj)5E5Hk71#02c{^;>tWTD1zh7J;rvj;%psYQ*Zb?;IgqGPNg$%~bAp&|CT(t4aecHLL*dAp|W7ki%2b(`$6 z_dG(>=WXC>DfrhkTT}kUHGpmI2FgLH=fWeUhd6$#6LCmRAc9SpE5ZLBK0L90{gzs7 ziOS|PP=HT-;uCN>Ui;eD!Yi)4^2$H@qsiC5{`EagdRJbsE8sb>6RyAh`b#dk{XZT+_`h0g5D)ywuH{( zBid_9?OJj^=<=XGwn4K8Eh`A)s1}6c!3Q4%{!iUZYWZA+aVsl*C3K#|(T{)pW1ztH zohLVy2;)X!bR9f=eyNl5QaGDnrrdtx59Q#_^G@Fap98mCvu2Gj9IbYHHlCLoUb2eH>~l*H8kwn8i{0y{aEM-_H? zF-bwhB@q^-f|8vJ8tn!)50+`Uzr23aM%c;^A36}^LQtLZ#p0TEYp18DK~%3^GY7C5#LWk`(17LQB`M-x()N!bA=LT z2;(Y9G+#y9iLfRvirY!29b+?C?k*Fdm#c#fs04fBEkh?YEAVs!#*l%pjN+~nTF@@# zcs0r!PZPjNi=u!cg1*3iKy&zdsf6e(U;yK&Bt;!HLTO4+hCl-kNNvMkI@suOXx&5T zMv3T~eh|`5K$$LV3bCNpJG#pbhFCb?NuUQ8YYs6lDglKEiQ_9j1-_o7`6A8^$X#E? z?6MpKdSSm|&w*;zbx^K;#$`tOUDRKfk=0mKGolPP1`{h(2YY#@bD({T6dHGwv7PyK ztbGeE9pq0)J>_??u7_CUNVt>=g1Dds@t@&;F@Ty2urn6bfO*tW8RQ}EWQvu=j2G%D z>Z=)8*3Sl;*3K!djN1!)sfMqJDCf!U#+2Dq4nzE@FI9jsx{gZ98nKDh(16EpLrko? zuyz8Jqn+dMJ1>yjZ3}z(CWT@Vn*)I^2sAE$!BbpXuEB%btrk{R6KwC$&=3r9d49Q4 z>W@2VATS%YUaMiJ(*y(5gXKPwa5?t%O46HS5_@)C>?z}N16HsY@`UL_3(CJ}oev2` zwFAKPINM)h)C0Qfg8jTiE0S+j9+ad#5 zR|4xvRN0@d+k{l!ZK{(=j!!l7?dmJ zVbN(|zbiP+^#=Uc0N!rBIb`S}59nZL+(2PN+Jr#Vy@U$W8ATj)APN{_n7sr42V19s z`NmNO8Wg2E*iQQ-L&sI!cuPH0;&qplXo{t$gr$(JG8eN@9)w2;FzmNrc}hvDC{6Ga z9n|7z9%aCLA&ls>)6N79^3dVgz%RhFL3j=I57&J}yqDa;mF!zi^z{fv>+s>j2M!!4 zmBhe68H`)*P^fhO&usiHxSyQcy7Pv34K+AJ!nCgx8qtK`Cve3B^L$r;R*J$=Ii&Wj4bo zVW!~wjisf&FkCx43>F2vt2SS4EX|Mfmu1}UD~9#@(nx z#YDS>TMc3Fi9`zSu#IQ$yJNLW;e6JFGzm%_lFAT(wnJE4sC?A`acGtUuT z8{_H`wmwQoUux2G*NzTP9z0NOHVT!pqUNJXAP34NuN-ui7E-?$=5T{Ypwgs>j-Cc( z%26hhI1-_d{gomknC5aN5!VoNUbI0r*3hdZiV=L)42E*TBt5IfGU!GEbo>7D(!%1c zyKe2@Te<9yU$te!_)C84`CB$^08OFYMpXIX!9ftkUgUM^BFrrn$^$UDa({`R)1m*0 z3L9DPz5m{`&OT#gWQ_6`lVT~)%L?2TwD-MtKTuz2_U|~k=+SYiFE;ai!vjc)O1ZE! zz3YcR_}ajh-`==+%UEB+)^D}CSO_a20(j@sDDhR|b?4{1SNcmRCi?%!Wx0VPA0I8b zxXj_-Hv;@9uU~LM@t}^4jrI4V`0TGBv_?Uql{G&%wYa!A7e~jA9n0qsEP7~g1Z;y< zBSUM~t{oj6tyC&E-E`B^(h?ZJu#fle-w!NfbZmU*&YiV7w-rHuXTFHprOQjpC`2ja z!w+(VAB*ZKND=mX!6ywWJOK6tvS(&yhCz?vnX}U~_uqei2-X$#ZpD;r(sJ0yq&(^o zU{&x}U`$wzQ^!uW&RQvdQlu_3?&GnG(1CpRcJqZKB4<^V1a^`o=%Sxj*FV!%N_*9 z<^g-bX^IR?Nm`M>d@8AHfMemvKcfR_BwjZoG+*d4LQv$>8?mQFp}4@!tN8{m^6v$0Nk^Gdfe*50d4MiNaDa{ z+5O43yKkz~S^H<#Ca#f6xquL1cv~0*i6~ag6+v8+PinOeM6)NGVH-OUqT>isAixAg zqtrl;N=&JWJOhs68vt+{+_t13+GYhjI=Nc9tH%%` zbsA3p(TIpJG%&Dz`}XEi&xx9(Zbe?G8+2MA*-hyuhJj zJyTEGHIlNc7nIANZOm45Wz%(mwPxJLW8A%2#qM2#D!XCvy|j#jOP==;4PS2AK;QEQoI|Rkh{lDmBmmbnZZQ z&(?8^au4}?@4Xk+cVuvgn?6Vrpyq84d;oWH+P3*P%Gt(t7Rtjk@u{{-l~G{11*z=4S)M}e5tg$5A6Rj*=}T%7VGaR8p5WH=gHcxB>% zP8c^JQ0R%kKEQMX=C(vq+mOh zylYgB>FXK{c86Oxhn3M{1;a_5taZE3ZKgxAqC2kLNbW!F7lnfYY_$t3LwnXyf5jxe zncq`u{R%`GX!;@Az=sYUqOx9u1%-uJy?XV97hVXQ@mtK1I6V3-gzO=kNI5_y7?|kRlYp-2By7mcAc*0Yj z^_){Tj@M_WzyJO3Uwhpxuz{cZ{O3OHX;0gE(zdv@yzk(|t+(F#)z5zxG~~Cx^=-f? z`bKiC*23j~@+a{7;X}J$^P1P({gbMzN=UcVuzj^=1CnhFt{mD)-$W_s93&@~KaK>iWC)f}#7~ zcm5ra{mY;K{8zs6m1;Qo-S2+)FW>Qdz}Y_a$g@b3}#*o+)FG zumTfNVubpD5lX)p z1|YgNt=}*|KhHUqKC6|4u*=Zw6y`t=EmHxjLk+w>{q#vXk|`+JrloW&9TO%8t>Xc; zW)+oil8j*evwFuBah<_22!ZLgxhNhKk2kP9#*1J3ww#`pzRPF2DSmO zNfP#rL86Dx5)uoSiJ%y|1X46=)gE$vdplhuq zVEzMo{S`a?g}#r#zLn`fDqzae7u@9nY_pU)-HU+mBoY-(xt$H3}tKRI5uw z@&S69&wZ7w5TZCM=DcIBpiEthmp=D7hY-DBk_~1$FA<+pnH_h%4UGy+n8h9=jtT=q zue;6?5Ib-tvNqeDxZT16mYG=uGOX9ytw>i|vPueK0@e;T{pjkkTW+~&!-jQ*fq}d3 z+PzSnU0hs*6VzzduKV`4fqGAQ>V-?=tm!}O{nl(^je3%Tk&G#Sgs;9_t08a;7!^_6YBbpfMys+>2b24v zi!Oo@+7-l$aPPG%P-SP?VgAIQd+YywyvO6NU6hDRl*Qiih!@7rL6a;*nDZtUl@XrS zj`5tiP)#Qzz=;R~+&RyC&hu}$;f7){|HB{N_P2li5qQyAXPx@wCqH?3)hKcyAA!eU zrS>1#_u0?NXh@J4IVDX5ZX-2P<(}>dfLEXYPv2b z3HQ>o2}H#8=zKG#gVf*%*v1bwrO&PP=w=_8Rm#|AV5o!0h?5Sxv;?Mj6k(wgYL`VP z)N4geVH9GLPzdvm3X`Dhq?qzDWaiQx8y*T*kKK3AU6Y3n!qcXvrtZIQFK7{cCCp_T z8yZGkVxUNgqooMW0y&9N)j^r2sf61gP03jUgf-4J-XRI6sncjdp`w(61ZJUIyGxB@ zL|zh1w_$7F!2IhR+P7Pbpb~``j`=bUa!E14H~SN|gd(T3EYw?H~W~Ywo@G-it53_{=lUvAdTmDHv$| zL>D`u*pvJ2cfY%@uMaqn4*aGDEF(Mhp7TW-vW_8eA7joFQFHS%%e5+Si0Z=PU;Xvp zoO$jOuKMIBCXY^i_``qqrnkNK%$*zi2M6xEfA69{@SeZ=urH%8ed$X#{phAsFMZ+i zV*MLm`_{`|`39KLwf}nU?Yr;XdD5EsrP|z$4@)s%q!pdjyvwSB0n9u#aXYbp$=cb!){;f+decOl624nkEpZ?O7 zSH9)duewxp7Di5a<8z*K+U&8ruKv_VPTq0)>tFZB*I#$@|MS1!{jqC4395xp&LdA3 zFlJpse`WeU@?~`orWovD5dCb^{!G&OgmVc(nGXUmTkb)a5M*geI23|TJ=+@Ajz#<( zbI_{Q>Ww$v2%j82eE592;FH0@LH;X9e@a-$F3X7EneeSVSsd2P=3)HIT803|2jiw@ z46QIgkOmpWI?vWrUMgvuLsskJx?1v|C-Xr|NkfGdA zkv$gp-9{6up*pDIb0onyWxM8Vebv6`sxNijkSjjv`p|l*UH)#wyjE-MJ^Bg6@|adu zmlfm}fvZ+UdV<|f?JH{(fTd@$et@PaX33&dNF8swDYM~PN8jgwZH^b-=<69EO3&8u z4IVYehk0Kbcdv9OrHrp#vNdArsL7yJ99v_vlQxW^4NfAElvJKI2izo~{IP|ggii5d zVCO7;E;z{+N0Q40rop3*0wn~}$f)xs=i@j)pO{<|z7sa*QijW-~CprBN z`;G8O6&hMHlg-Kjy|kj*rRPdtuMH^KwYHR$-BC(q@LITc7QfV!TC-$L9d5>>*J=e6 z(E@FglOt^N4^#&!Lz3`Qa4>xX15#$eSV3+)E|wD%yMy~N`!ozei?T_)oH)%PacM%n zUEyEzP&9z?5BOou%Y3e$Q)5qwwHlj(m$;uUj|#)$1S>q3tBbbK)T7+agz%_LazwTd z69X}2-(^pe4Y%?t$7xn`-bq*+_8FVRGd1dZkgnyU68i*RECvL^5DmFkxFl5=7pYlI z#RsQJmq+l(7Uq|K(M-k|zy!#m>x$tkoTgzKQgrPob>bReS7m%mDbhV!sdDOI1DYeJ z(eg|=g33W%V5_j@LW2GCjF%l&laDq?IBj5tAqREguk~6jEF+jI*A&!ih`bFdBl8@t z#N)nDAY8nt&BhD?DAs7nD3p|Bc_JL=hwXuVzoiE|YR#H8Xb!cS?A)=DUP|-SzF`|o z!-bH#R6C0=>Fugq?Od75T@HOG_xL#;80Shp;C^o096&+jRI%w&%OinFf%dR%+qNS| z4)gf?`mpMR_Z1hj2$C0Y8_*CaS*-N@|O4;4x-?s<#RYXEJ_08(tt({2{Ql=RNOv@Uu{=oPPT0 zx7~KzsXI5e8jT%0cARtJh1<7pPNFtg2-p704ZrnUFND1`IywrE*s*iNUrm# zcjUeY_V3?+&f~WODd16WeB&F7qu8PhzP^9|!LjWF6B85b)~y4JquyA84}p&X$NOJz zeiMvjdA8a=+6PZ#Z3hN<*8lo*p*j;Y6N=h-qC_GULLqE{0E=t)?%i*Gk!hhe(nnkeOunL@4%L%y_*X=|Xw);7Hbb5LkKX8H=n8C1x=I7@*I|J^tg2{98 zuvk~&uiSa(o$#oqJmo2j)9Ioxp6Cj=Ct;WmXXj^C+C;I@Y60JQ+|H8_^`x&K)RDsa zjj$t+9h-*9OwUcT3R|l5!}&yKe4)5z=Xj~Fh`lS?7>PbSaqQeP&#hGYVf0%zYy`Ga z0CoV3snbrH4FQ^N91r#tD@B+yrZNiZ4OnY}K!@EQ11TquO~L|zv5iH8q_2Zgd*m4A zAo*c1zIF{9yfB|T>zuPkMuuR_b8~a7TEXesbJyMQ%sqSVJ9=~~ALg(PozR$)WW0gZ z=aahW5tcef8oSUD4SQwYdVJ@HGzq|V8T22h+EW@N5`-6NW6SkYu9PMzgQL_MHB9+# zBUAF-sFYw#|8c7f1EE9~ouB2iaqv6T ziYU-CZ&Kj!{#0m~C2QogS`Cmmf-F^Z_4z(*QMC5+L7ZTyozio&EH8beg|=X=%?av@ zA9`G~Cv+AY_lWly51bTbY0WCD2=-_Lc6ECGl$xvOpjwsGY6Gd0cu7Te+GzB2cV2E+ zkibGx)o!Q0*sf!!01vz`5o3&b6C1HRQ=GAJg#6TR!R5Mmx#%3M?VKS%62bKif z3bqO;&~RI|hJ^!)G)^~97=zm8KWgMlY0~J9A@n8!8}n3P-=(rV1Gp>4%O2)(VWAl0 z%YLq;yqxmF%L|%%Oh~18M4bN<8&c86_ot*Q)9$wBz(25~Q{iIWGbsBJfTOARr#7`529XMGj z$Nrl>1%DNHEbn-_?-vMz4*W-_MlUhj_PIik=F+&9dZzbdO5J+6OoRDM;1k8Xt}Zf< zU6(q}<#Lh}-C!b4xMP=^OX!kYtfFBFjJO?>NdW9KMv#0qKST%d@WKG7GI3}E^pF0L zp_!?pr091zQ)KbjQBY2A{=pAWpnAdBVBgx&Aq>ZXq0s?tyuLg$6Sw0+Sdbwefkv|y z#qD~t;ej5bI+(kT;WKS$u_-&gYBTJ`M~adF01yC4L_t*EfDRY1QVj66Tg_U%5auey z5-qC?8X-A$F@Kv=u(T6|*1|Fe8^e^c>s(tKQmoKrIRgTPmQuRRBDg8G92*`xY3oVnoOxEx&mB90r2%)`cF&J*yr)nC_1dFm zz(8&>IoSf08|<=Q|MjOm{_&3o&JUl@&d#!#L^E>o1A}no+xho?a_FLLN`{ z&w3_MuQ=}}rJNmuol6nX7(s?xjdlmNXp;>11oZWk-BM`GnoJ_jS28c9WOAJsM)F0& zmEp)mt0CfcAahZ(*;gp$J>5btA<2T?Q%d`xMDdOyhJc@GBbJ^?31FT|v^$ql1r#DV zGjJv`bu3u`GC|G0joBHdE7(09u_d5!&B`dCfnj6-@2PYr+;rDO-@)xfy&p$Xe@l^E4y#J z@y0Z{9Y@=LffVIXE#yS4(HT_jbQ$x3nlRN{Z@n20Nrdt2b=nP;BqQKt_@$xZOryYIf+@~-rFCA-&Oe?8ce@Rjd< z?|Wsciu%^Kz6D1Tb|46&m%QX9mJzw?wCK)qf8c=!KJ%H+z~)Tg0O)4-Vi~ zQi#=g=biV&^Up#Rmi$;BdEZ~d{K19rzggfYd&MY+gJ_R6WqM&VSI9@k}9^?uzX6lXUIpVk$^ELZ(#CV zVj>cm;gl-d!;lO3bv%urICOHO)Bf7;V^0br>tYr$=jsFjn!ccwc$S(jWzR4%{%aT;`b`IdWur0lUO=QV&`%NUkuZpe`ty z{r!U==U|mF0U`1+NhfIopWnWHJGz;DlrLEGLK#h*+9S*<;DIr1;T|e%!RlEsfZ>x$ z5mir%1`J=}ZmuvqI4P{raz;9LrRLjsMa)umRqeXxS~!V6J!jwU#>`uB0%|kny!OEf zZWBsb3~6E?#j01*sKAeCHL>& z&;3X}1B2}HSext$q~i#AYI>oeUq+->h_qS?Rzz}(Bbl*2DO?|)<56;A=E4D=b7#GB zYe^~v@*Om6;T*%B4bRLiB}X-lQ}U`YACo39i>ca}+m5`egGmNp!&61B(#(Ojgi@x% zu<$uDN?90`t}Mur$B5P*C9+0@F3x#Ik?0VIp)vWwI!4)L##g|2;7<2!r5ycCIs_3Z z*J~)#VVl{Vd8{U*rH`i@GCLSlXzK=1npIRW;S#+Y(FP_{R0n|x>XLq;ehi-Jwa4G) zxN%QHG0(yL$S(U=rAerNm%30lw$tH1+0p~I{)_X)G9|>EFV9KJFt5x0Y6$YE`5{NW z$*JJ`AxlGS*h!cUf(m`%6VRJs+i%;pElFbTCE*zWQG5JXYSOHDuqJuUHP<}j8PC|f zd2^*wK>z|u^7n-A48*t3;bS93Zz&_NsmaO7r=Iugu;oF2hOsf%f@gwE?CTpC85zhm zXXfYU4<9~UP0kwf5iSSr93Jjd)!EIDf8rl)eEi$r{)TI={@h1D`qAHe`9;8KLAU?M zfBam3A3~9lr&la=4lu8#%u@38c=5UCp8NSbcHMsa?Vv)ReDcX~+pb-^Zn@>wSHJqz zXPkTGUAKSd?>>Dea1K$zK%bv$vL?pL*eR!+^1~ay4m^DGhT&F%&0;`57YSxU0WmS< zWB_;+CJJEzHZrsWzj4X4yqpMCxMk~xx4rFc!1Uhx{tsPu-F27#_V49#9!wnWj1=ao z{P@Q|{>#7o%h6STc<|wafA`+orPM4AURMeQsQRa!cG|bU_EALF>clb^R7q!p1usz| z>aVV!;~E(mdB;26!3PAE<_&Ln0~mDgeeZiYqHAwU9ON275nx#BnVFeeZ@u;W^Unth zjtlNU)^FOhi8GISPLO>9?EHJ^;$SZ$H-SX^{`bER+X?;&2C(c-n@yd(B=`jm2yC#E zPCDtC&wM6~7G5d{Aslo7>NNRCSFkWQkHvgRd*}Lft1FeMsVT4uo2^#=a0L!nxsnG` zEG^H0G6Wh-*pVB;wTR7_FIMLlhbsL8rApjvr|rl~)cDA%QnB1uC{+rjoCJj;Et6j2 zW9$y|rKgV_En(N96sFf{HH!J%!0=GM5ax@eM#G=0Ewx%TpaKlK+Ng6@A=cC(q-Ptb zH#Rgjee@V;KURFg%>x5{*5%A>ixbA~yYD`(C1Z~`&z9LPtKgoM1KhdM3tYpJq>(F+ zwGx(bWb;7bB%66o(w)tgOijv`G>A(4d)^Q8L70-@WK0)(Spy^K?ojVuR-Cg*&pG6* zQbCQi(p_Wfvhl&mEFf&7bhGkXfz>hsPp(a0hMXXyp@+SaXJ;TA!Mg)(=Afn zkbZ#0gtV?%ag^Fupfuprj(TNg-zY2o6 zYOR^1tC}s5%gcPB)vEHyfyXhC$wbo;R5~F@zl3UpvE&g%5mh=#9nANvrz3S>Zzyda zE6rhJO(IYdfj`WJyTq7z2Ndi9yYLA!03|_l2VC>ZGxyea-6kEk=aBG|K*5-r3Q{zhA zN7z)ywV7SYxEqgSO`y`yC-^dK7ujfFE>EsF(2ps&)oLC7NcJq2@Y|#qIEI+uM2^vN zt{@nUs?`Rz)}Z9_0va$f%;#1O_m2(tFE62BOIjFO4}uCvkb%*4%L|KZ&K@u1@CYcZmx0ufik>OD9x?CmKJXSSFrst^i~! z6=XJ?zNw?f5=^c1=I1f8G(JAAB(8!?M5}{)5;VWVhmU|bhJnw_Ou=Tup;D04<3y*_ zK_1F17C6w6N)bZ>$tC=#T~BG3aw|CC;RymRDBml<*=QoZF$ETJkk;DI>=S#GgyX2P zPAFlxpLGIyPL{8wt!FBPHMLY`a_}}&+MlT3PAASo2nmTrG%@A26UG$qjF3Gtn5Z8j zzE?~r1I7-|SOgoBc#42S5d@vilthk2xbA6^3-ib}6uc=3sjXvxz5z5KNn|6AGu%!x z0asLcnYn0{0b~(e%;K>K<$k&3xt5-FzNaR7OgEvX$ZiWQP`Fwf#~-uFPk)M;HfZ}I zi7?3;TQu;dR9zf`tzXLW$NzXiOpKPP-5Ug^ngE?O?OMzBax&hsziR!U8!}osSZEeX z(AFT>2lj9+du)%(%^uZ79u9<1NE41afN{l%$~1u7%U<^TzwUA*ouD<$ec)~Zn@eOzs7Zxd*&n`w%QXlE05g-?9^ zlJviH?YGvh+YCC+^wH^S{_1c3`0XF4PS>inr7#!t_YbaG)!MdY)4>D#Pda)1p+kq> z^S|GE<&{^Se)_3%3wJEcSBnKO5n($fL2fV%mL9)$+dp0X`QN$X&z4HTP%0`(X>RIR zrI2qPec+!z_vQQVOZv*bD3-!<4yXm9s#9-Q^5sHb|Hf_GH?7;W_ny7$S3miId-v|X zYwug$@&cecyjRTD%S{0SZGNURGgmG5jqKZZ+vJghr=GR5)@bZ~aPmuE`qJzF`Zc)WtdqB?O-pl!000mGNklo3LR|i~H^UM{Q6mg>-|rry>sQw! zUqCU=Nrq#>-RW%Va?e?CtzTA|;5h8uxwA~yjvYI=H!Zf9rYLETc(oQRoSl2`y%!8! z5c=@07ryX?n>TL;X8XVc4}9~R-(+yd+itt4m^4GrhwP8-SmKF+?T>seP?*GZZeDH%Gy#4lD;eBHxW0>n7>bBtU z4xZu2$Osy-oen3Hz~`r*emXqr@WhdQ`}XBRgmK<^>M6i+7#bcMlogB9)6?W6i{J@d z+{}3?a6XS7Jvv`shM!yu$8ZAF@dYcCDCM;e{@Q6`?Dv8TF5ujB!j7&{%mk?kufF^4 zyTA9{@ACSw(nDT4Aq+F+04W=aY3u+$ILfgT2FRApl2V!)8ZLBobu8>S(Lfyq|F_YA zbp^`sdwu2G+9Womcw4aOwFamAG&_i%HFL&^dOX{`{8JnD=8LJR#*rGBkv#gw&bM>% zOsS{OHVyd*T{8?vsFkW-wr+X7(Nwz3KVb}Y8_=_FOifbp$_;H-M0BfJyersW02_eA zK^7*IpJ^37YdrTnkZxm0FnXivnocHhRhQ4gT?J`EQpTKC_695aT@TqxIohK{_I&8B zyJsqRd978-{Vj2732mVcCQr0MIO1U}RLEgOZzMNP!Z0Az3zwX>X&`k%0qo7GsUHju zR)EXEQG#QRjXmgetn|e9jLMSNC_0+99G9@ljVH-RF12^Yf-v*hOcIKp_@>W?bD_HL zM3%UESvd8;*7UX8hL^$aKqS7OHPKO~k*}q>J_yE@5-(QA*!Y>@;fhUt}jtcpZ8c|rs8D=e#&kjosvHurUzf;w5 zw)cAClf8R&#TxxgtA-2-{RMZPvQLtM+DxfCkvflxAYG|Lf$3=V2-dHA?%aEv-TSD| zn&Jt->cp%$z-a=qKk+^wLYOzyA7buDRy-fB*NlY}pdUiJi6m3Sa4oYf^Xb-VNsWKp;-vx(aT* z?6S-L?jQcY&wcK5QEBA$uYdhnr)@ZNv|jPVi(mX=F@DDDUiZ3ot?}Ex{oB9s;+GBh zqHq#kuYUEbCnhF#p1$)fZ+Q#Ipv~(xKkHe;pZLTlcK_r@Teog~=}TWq(Oraw0YMK_ z7#PCfTYrMNlVEiKTL$`6qsCBJI^~p8&OZC>H@)dias9Tl>6)8sjtwNwdCqg*{mu{H zamO96e$C5(XxKD+{rW%qvp@U52R`tT5C08ts!J}pWaDY8L~9<)Au0PNI#TB|gJf%*;as{f?}275qwyD1s#OWtcG5x z5ab@Z`|eKXj(_~zXO^dD&VJnEND@b_Mt!iaf7`Y#zxLD%vE#zP0IMKygy5|((4$jR zyLRo0JDAK?EaY~MJ@gPvV`gsFliu{goID&f+wELmad2=LSkKht z1WbG1fd^7d=qhm^7iB`AZ2c-qrH<3&!e6^E7lc&(O8m87 z|N4zL-uU3YDVTe?i0RX)Ln;E*RoWL0+I@~3kW^0!Evl0m-~A*1s8*a zNx*SckaM{Z{tFHERS;w~jm84haCoG$NGkG_o+$*v2sC|SowA^xV6LN2PHn_hjCC3` z6=+c>NJ$Z7#x)ik<1%&{cS}lH7P8{b_7sJev!qsGgd9sll4=@-impsl3`f{@trGGl1ikKG1iKi9aEH# zM!*qu>{tvI5%sn9(fP#{6R_Z%R!J@((z=o~iLuTw@PcBo4Ej7AAJEMU1n1LEu%%6c z>F_B-X}ioz8c&3jQn%{np_m)2PAo{Nb&1b;3SCh?YKX-X2A+EyBJ)mYI0G)O$w7en;9hkP(=$NDoC#?LjtRVlcMU zwDmhFPYRD2Si6d{NMPSZbd*A%Z>LQ`U}T=pgOAsTC1A;wcYyz?3vb(Ei z*NN`R1sg_CY1Tc?I@;(?V^tcys(+@GW5j*weI!jm<>1?3VnQe7F zIhC#fW;egJx@p`53LpbyMYJ+#qfjSd1y&W#?9OiichrKtCu_QU~#3CXy-&L>9uIhVwre~&yGrUFd zl(ganikArP0x}J2?S-LTh!C;=2)lwLKoUU17GPL_my)bq+X4i^>s`@?C}~9qvH%K0 z(j-MKhu83!qo?og>h7xQuBun>&W!MPM0^>U?^Vr=L@kyU6OGre^5qf77hinm?*q2h z=`4QqqaOn$>bu|lF7F*I?t_d9iwm^bpZ(dN0|p4v1#opn_^VB;q9iGJ)VII=?Js@l zOQ0p5J9iEq_@{sRr);@HenMMtP5X@>f?Ps}3cxM};@KbeA9?(-o&KcVZcI0yUq5&5 z*M9ZCPg||2Ho$0Z?2g(E)jam_$A0nSclVNy{megBq5FOOfB2!F{zq^7&_6kTdUZ4= zWuSRispVI{a`_Yg>f_9)!X}X~FP{0G-})aERYzWG8aEvtOb*`jEc?u;S)II?vseUiy*p_OH?v)w|Bd_|45t%)jk4Ii(8C?HlNNW<`#7 zFIKOwUcD;S(m?Ek>lYW7$?=4Kfc5otcn)WO9Sks2%Veme-P_%TPloM+WzR-9#_;3< zzsQv=4PlBAZy1EJv1h#eW9u|X9YpdKUN~Q%tw!uKbDiVuH z+Vj=|7C;kSIe5z#t;S1#gb2m?iY8_zC5p@?5(s<~k%az4k`NR!0ood#RJBiFhL9$YXf}7rb7C<(ND_vS`OO3Fh>UsVY$tlI6r2!fqdaGQ~Mh#%Mqo_L_)C+R9Q<+P(Ogl+F!T zb&Ij5T}FVTHvIDO1-HDJA7c_y4@)i?ecC69c@^D-NDYuVU^yS$-@}p;tq!j*8~=dmPRnvRLCQ4d_?>eUs+6D zB1Fd17ZgSO-fDSJ2DS(Y7y;}xurUGqf)>Irq=$3fHF?yH-xoQ7S%tO6#dzI<->Aen z44ipkVS!ykY`5YU!8QTH4b=fkK@fvKdGt720g#xl000mGNkl!LNmA-3O!cwMr?57^EJFD3LjI#m#7Y$uS5`RS)?%X01{$_3J%aHHiu@p1nzP{u^~@% zv^!XaZ!FmhKbe8hyg8Lv=tq9!AH42$uhTw6CFSj#xDyI#aKS?lJrs4Yj_=)Ww|l+b8{Y7S zx4-@Ed_Am}4}bW>D%4oAc_FD)FY)-9fBH{V)*KU@Ugyj!)ZlK~Ii3#(d80M4_UuZl zhXXKGSRcWcje#WuJa;%!Es}LX`<)KeU^G};?M_wF8(lHOhZa_OG*rKj{;KXmw!DG` zX~y?da}9Slpf*IYP7p)@xb{B&*VKf-I_;~y{_Twu4~*y;t&I(k8`Ok?3NqCn?6;c8 zmkQNwBxpBJ6J_?4T2cByt43>#G#KnGPEB+5(SQEWRo1e3qnIL+BAh>d;vA0Wf;yQU z2bxG4YS2R+9Lu(u76yk?Y|iR3bVFloGcfIi&JySgc1RCS$&xc+9hd@zT$9qBf1v&T z4GtjnPkiDNKmYSTuP6$SW3^x*|N5{0I)h`)Jw$h4QHOaWGi{EvmEgO%$8*m;_s4(y z$8hC?4?cMD;zjs`+rRUj?|@VQPx$@c|NRer=tFOQ^P6kgyfy^4G6RI?!?yL?zm16Q zjxfV{A9>L=n8J340*<+a3}{eS(}aOcj}-DZ}Khy9(MogaSFTM&wRYy159^FQ&y z_XCODy>$y(xpn&vY>>BZ-MDn=BIdiMW?=ze+3H|*qVdR`J@tbR*Y6rIM&hLM};6L9h&M zIOds+kz}ZL9yK0z?yRAMfW~m3ioC(T3=+8&wBSsNV6B35;zA7raaph*gS@@ook%Wh zs;f*`)BIurL1t)S6{4A`7*e<6WuT?5SGKKdHyc6F(d0D4T9p*^8(+RJ04^)-0tjS*MF-fzoCR1y4AiCKS7FfmRFc8e~n!0-mrvr=5FS z_iauoyAzCpE^@TLuAh&A{k2vjo67q;^%pp zPT+gaiUbx5!6ZST`^>Ap?7<_t^nxM!WzCfEO+Wd`fA_JEeGCTk{qKK2tWC6M4|>q% z8#k_z@e)he!9C3u*8Z^`n8s2zqiZ2jJ?4hx<4M-Va@2yfC#;#2o^kQwA(41<$6S>V1+g| z$>A&*w5-t^v5dT2T-s>e0Gy%mW-^L2>I@qC+9aU2ASPhlWBuJ3C(>I%`JINJp&5LXYT&iXuI z@8u)wt#yo+l%h~>*-u+gE^HwY4y-%nMUL{Z(#;Hno}66wBV#zrAR7*WS0q5!q&zzW zBT7)WoWL#65*{>5K{^KYv#_xuepOlQ9o?opBe)9{Fft?{D2i?(6adX3fuvEBLtdc| z+0mxhAoP2xzlT`Rv^HrB*a7U9q@}oP=BP-I@ESvP*RiTp;?;Yc1Jq{=4Aa8VV+?Yv zlbjG_*EGW%3Nt15a?VAA$vq2HZE=eOMwJj<71f{w31(($vvG8dry1Iio#%OS%iO~S zJMtL#w!uR8!0V{-!DLDE$UkAaL8t<)X5gT7WUQ}QSX7V-bVcf*FNv`PPJzAU!p6#R z&sk~$>G50N`qsPN^)BXtig+C_^R>0LXPvfA4&dj~Hn^Sz zZuTW0VS@x^=9ggMWF4*nt_(Aarq9v_l9uZ_$8m#bH&e&qHpK$01z3ZN%j=6tPLX$t z&?44aDrr6h-$AQ{)w8zJrSm7dEv3tpNwq-b=*HG1DoL$EjN~csp_WUg+Jl$ls4hnK z#cV;XFT4`Iw0NRgRE0Ggqu0!WpxYqWz7`?NC|Gm2q`MjJjqPqe7-pt{aBoI0HWg!1 zIo$y&uq0dsUmh#SAQZrQaL|Qj%d}uHO&9B=0}bn>kz~w6b=E1C(6Q73H5$Z{f~#j^ zhS3z1-c)xj;;g%fwQ}I6mG6Or9f_gw_u_~JV-sKq-~iEue}!eTK=76-#5UJ%udNG2 zZtC^E`qi&~@Pi+G=9yW0x4-v$zXvSz*s)`O@+W@+%Zjs>;1;;? z`0?YffBox^F6Yb38Ls*4XFm%Ikj+wDmz()dP5l<-Ss@74{rdAQ-u3V~P{F_TooC?B_0_d^zx&;v{-ZyFXMN?b{~B&Pb^HV`3n~wftN3>u85p27={@6Dt@NH5`lQ z-TMcW6@#MaB=RL5M;!uL3tx{1gULuB#(W0gl5ADwXfzYy!K$DyISSa8CtII5lyKf@ zOmpF-R&*iXW>S6%y52?;%=#p|+{;==!5R%66@RZ6ixmql70)LcWlcd@&0EJLIsuoE2}BCPW*I(P&8ORIQ~u~dpv;PZ~kJ(3r2t*I^?Hi9HI z@wB_rjxLkVG4ayzct4Jx&yStZ!9T_6g(?Kf#?vjTm!65ulfjWQwRg>(1;m8x_3j5rvy9LY$);nsO6s?eu#{gt|2~mcFx-L=T zm3A_<``|8TYHTIYp108;i8c`SnO%Rft%j7#f_(yG!mUwcalC%xD#$3qeh({tcNcU> z-(_)GM%6@cbTXuIftJ~Pl_Lz0Hq;LFS&=lM1!w;TWy^n&Kj}8ySDQ(*(HtKPZ{N7} zYrps_=|cM>ANj~T-ti7pQN{ycO=r%W0*(jklwF!!y*X|Y4wOlR{?$zGy7Zm=oF&*8 zE5NEMFWQg;?*bOO3%J(uYWS0j#<2nnd{vPwI2;zff056J3}h9f4-YS=vauL?<;oRk z3G6-akku2*uw!K%l)Uti3hI!ZF=S_;cSs>dmC5tL*47rBWT-|M{N?2?7lo3lMOXzZ z(21Cn*c?GFM8@+g*LZwovw>bg8F@Z98HtCK<0DE(lPY~~Ov&uO@~^C_tTNi3pTtv8 zF?jJE%poI4WcCVr9omnpNF?El6=LQkBSITDNCpIyWV*%5;!ND89yp*kkSve^Ft7{z-5pfHE;LuZ;C_XYf%KF@#*K|23~HDtCqCz3A$|rc5*OR2qHM8<}RX^fz!|dIZre^Ak!>AE&(aoI_ji96mIg?Swbd8j&P)5$Da=I$?N^ab z3#*KwH()7&AQT6^#wJykB z&%j;JKmYt+{^ef+L7qN+8Wc}BDR8{Cm&PqgAA0bCPyONl-P^gfdv9kt9Nf8iP&zihKCshoJ><4G7;aT)x71Fce;exzPuMo|9lyjl%@m((>|3V*zFH zw2^_X+i0K|Jsu#cGpO7!D2j4RoPKUv(e6bYj{a}G&YvvXG(`GxMWQ*})4; znCp!*2r7rU(!#`!qB`kV3L$T%_L0x5q<|!!X2E&Eyc4g~#dO?iHTDnoVduMf{Ynd= z4$aylk0zbgWH`!;UNZ&iI|f_P`ts_@V;lQ>;{>#|9BZ}#5yC*VP2-hMJht3jxO?~R zXk_l)+n$cmKLdkC(KHl)foQ%&?9^0C*>hxnKu1cZOEX1$-oY4K6JnZ3OP|t?Pt7A3 zX`k{#UUv#%qc0SD0HZXea&d{_eH=qMS6shUCjdVm-`?=gq&WtjF2g`eIGZx$gNqT@ zLi5C7kJyqfnJT~i=Ekt992|Rf=tqB~(V2AiDZoUmhT``(j3` z4g7)?V6y!??g=!B2a&f-ETYTlOj)+SJHRL^S`cZd|4t%oDHM_^&~r~tnq|Ox%{Vu- z0=+@H7_wBfzrW9QP(TwVR|ybA!YRsrzqekg%k#2mP?A&jE`CnUn|dYOslmS3Ek1rp!t)0p1(7Wlz4lz@z_zKd9u*SX81`c z9!9`6IpPVE{3KK%emNZmp*G0Y&M|zH0%ByGR*@Mpc1jeI($8w7I5^@j^s+L(IDOn#wsTF{cjr`$ zDq#X7fwW(Hn5Z%xo&V$tmEsur_xxaQcgW84d%u`KNZ2iwKB7qIVOX~9JdII=#BB7qHsBbQ_e zFcq=gL>P~E#*03zU6$lAmBRU6uRk8E-Q8WT5@drHT{x1~6_=)qJQzZCtbZN0_Y3{o zsF05iQ=_WluV2N%a2AuU5OX+R!GfAS_!oIj2r;Dwa8DxzI6RrU%*wo1x!FAGczG~hys*No0*iFv5Zq=qJh{kMk2@FF zCP*p`uoTllJ~uX|6ygM~Zgb2i*oZ)Thvl7!B@lXA&V1NVbv-Lf$q}xfbKc??nE5<4 zxH33?DuOq=bVa&=Dj&NU#9ungx@%u#u4@~gpEC6lUBQlV;G9Nl8t{RY6<|b`ML71W z$12yt!Xk3AK|jkBJAQRA%Fp%X+7R#@pPY3J%pN*eQAK$ZE%vZGsvrKpm+P*t9EpE~ zv*KkaEy6y+YpyT(WxaLI#q~?&CecE?e*lzlbmJtLqGIGY)j&Y5FYS|R|>4YxRenquFSV#qX!l5ZEt%U z1A?rrtx+iiw5_m?2^twUj1O6r@W~f|r19=|zgsR~q&m?=YWkFXPtTt|JL&axf4q{l zM*aRH$Ira(kyk*k&c6B0(C23^zwn2D_=nK9OP4M^@W6xY=3ZG_yS;r6^z7Ha@y($0 zciOGtBtLQH9Qr6Uwx+XmY&@M_zIy$e-}(+0%ovR(tRJ%Lvejx#3d33`M@XVvm^DFI z=h`8SRuhEC<>f_aEA$++?k_$0`RmuOU%PSz#L83~UvONh)ulF-g2=^ZBYTeu9(LZA zL@40+Oh*|E2UVnU(=bs;HR=B?w^))Mj! z8t^Hz*u+1@pDd2>*t#ecmJg{{6w6FDmo~hyn~9m7{<1u$GV^=&yKb<)y>y$ zE5ULi7|A$`lo^J?#4U;YE{Gzac2=!jKbLaNppbv{TQ>auNUt2%^z=Qep_ZK?L z_cu4!*G`CG0%gHe*Jz2#jK;EAT|lu_#8>VV$2P<2M3YT-k%Rn2>u{vl>}=gaM9rta z3FQ6VXTE*!{&p)%cXqZ^ND&lWg#|kxK<80X#d6FID2uh0HG3$wGakcI;i-p#1UZZY z1Vsl9x5bZ$M?tZM)I!t#^4j{|-R;kQ_OoC8>Q^6q^!!i%^iRW*1-{IQ`aaj4+L^Ia zjiN$^Lo{3T2M8`OY>wdM(oz?ulNY;C2#!PKULfCKA-xm5Zkmsw`>gS@HKCv&b4L(L zlL-QQ2^sPvCzP!wo(UI%BprDIP-q{cuOeH;{0op2$xDt`_sOPdT0j{3^oi5Jy$3UOAF5P_S^yW_1xO;Om(`rhzh`FwX4k{^#smOEhB0}!fGpe#7NW8*Tv}I8a z<5kIIAD-{Sk(}4+5s^Tf0zGxkYyG5$AriKsd`Vy635EMY^fI5)qIj$+goK7zJL2TX zjdE$K*1;OY+|041jP`e5Z%vwqQ$(|j2zCWk`t{l1M4d({R+cfkl{qM7Q#&(tsPuZ_ z0rrzDAtW}<(3Qrwn|Zztb%tTa1X0G33a2HsN;4_~w^`+Eoi8nYUQh{hp@Qb@LS~gcs*TP&`smqYk5*HPqR_mFhbuyen7lh2Y1j?@Tgu;xaABoA zhqAY=AJz>I)W>Oy9juEzV=Ag6(DsDgOU&J{)Ztr%lSN38ww zV_9*P*TF6D5ReVnRZ|eQoFbp4iV(I`SnTo2Vn?(M2^W0CGQT}!(o+!D(H*qB42}M= zH~kPWtjAyd7~J#Zm;PVa62AQ9FN0DJe}WA0hBv$sF21+D0}|euGiN~D`SJI?5B2^g zhO0gE{6*;P!r~H~-`^X2;R|25e&t(O*{F#Lv5iIxp2lU7S>xq;p*qBZLK{w>J@?Q< z58b|f8+x+1yp&KC$0whB5*`Zz<-z_Q0<<8;vT9{y`_Ex~5xs-mPP$CftHv@#YAX9! zI3^Ii(>HE_gai^9g03`C&>0TKtg7*RNNAY~PA%EmU6IRq*}v&sR?o9}8$HWT<{vs@ z^bN8XNVPgINk=NjtRk($L4jvJ1e#?Oj2jk|7hOlhjZLl6^0*hWImI0mZCng3d;y!H z`LMxNu7W$R2#MCQt}77^L7OVg|M5Ol+a}{{Se&h`ji8N}1&!j_iIraInvTG_`F817 ztQ(6Yt)n7IJWbr$SB%o#zkdB^fA*gNt9kp|-!7adelKb&cpg4|4J5dx z*Xu1TwDV9eO)+jNFL`HWL4oqie2lji6&O_3NQA#pVK&AeQYy~(BUVYi4kPub6k2nA zx*+L0jFYE|scIcVOYqv-8rg%XydEhGxwrbEfdjZYq7q?2o8U^`LV|yQv|bNbIX<^WD6NrFY)FxTuq7SiHdtAj40ggeQV1iFRuy?n|$_GN0ViHiVJ zOG%OB!0b2#og)DEKnTAV0>vsx6v_*(9nBb2igzsbGt10I24&9#X4Se_C6-@fMkptB zs0YCoH*S@UyuNYt%`BA)NtkMoWO%ra*OZ&7K^+sMi}s`Vyl{SFqQx5pWw@D*?68w_ zk9hsgp7)KR<{48DH=rSQKBg$Ny{3a!|E3XRC6?!oezSo#MALKLo*UF)VnQZ_;~&+# zFh$HWeM;TjYpbb$vrm{kYNIq~*a_QTdmUP$3;60oANzfG9Hy8Zb{yg3`JNmi*&;T0 z&~IgzL=Fj-MhEkUAuGpJ_R|i z<)FHzokt#h<#2CsdwUN?s@I=(7mq<>`@`uZ-(6if)@(0Ki`%Qm)_T1@#_u=IwmXS+yIb39D=Ynee=->A!Zr~x(89m|-ag^ZfxKojW2a-+ zYUsh(<>Q>Ok`fH=)j4t&=^FQ$%*2e}NZab5cd(yk#l(lFgUn>e;yxaaWQJl!W*oC5 z+&463D*A$vy0lDz^hCCC)^h7*9{uhYg_ijl;#@FS&!=*J15>C1WCT~$$lyyO@&MQP zg(k2EPk)%BM3x0^c%VQobriU$gxWHFup;VpP91g^W5m0w*rF!;t88p#1A-K`R6u@s3)9knJ1@)atGZt*(d9AJrLE&^hQye|HXmwJ5g z1KHcgjz?~QNQyN!7fX<{3zeHbJH?K0Vk!9(g&A8Q(r1fJz-R|GY$O9+0%M`A?q-P4 z2>(FuMR==DyN}gTO?#=^a7nY-zPF9F%An;~LP=>@m8^3rRpCuUQ)O;;7y%=5?OWFF`}@73 z)w0dDg;`7~jDkzpYTtfZK8|+_P$Riw4Z}FYCqq_%UabRY7e;*K$Rt6b=5R+m2?Lz^ zkeq3ebHKS`+A`iRgeOup9_QU|Dcve^KB0w(lqQ3<$C8Fg7MiVQ7hw@iu5Df{wmMjw zx{oO&qx~WLYcDL1dI#Ok+UTG^?Csjg&^WWY*fn<2OdM8-h5Iu+5~2h`*;mZ;wb#YS$!raUL309*Uk;I$MXR2i zYliZviD4EjaHmOHOi7aqIx5qsanTYZ2=d~sTz787%FV!TfwjHl) z5xg?0V30eCV^WAQX)(4G#;6jUQmR$>Mw~v)1p}z;6`W*Sm!BsUY2!3NYzxvvZJdM6 zmCJD?#6*F9XqN=3JR#sXj8Z8mzce9&)>J)sO6fV|3k^09HVre;5pU0Fr;aKDvOJ)3 z8XP2jA2O>F9%|C)H1Eh|ojF)QFjNJa&K%n}Qa_9o>0_Lv>R19{;?*@9>Ehjip|89| zn1{%pF{gAP5TFPZkA(forZ3x^jJ(`?n2^AGU%aWaWWg>6xkknDcPxDKSGgd3nUzvX z(IRS(lAX8e$W`->BjoJbHI9Z!dD$|S03|v)jE&}KGDZN(=>;h=s3KG4$cJjvVFb99 z)m9lL_9cqK)&XXZ#?8sw*|AbYMml!bhpe5#KSIWVk|Yp#Ky+{Bb^bg*q4ddHqK_l>EBa*PkE;)p}O~C4tl^d@qcZhkV_9&5obuh5T`ZGtmaZ+u3nG!Q@ zg?6Jpmnhtus|M=9` zLDKs4r$5aK!>eEYYR=Y!mW}DSfB*jNt-Dxo!Wo7s-rCwaaRQ^J+szh8K_CQ!sLg(0 zVCAg7!+X!1IdkgNsm;whU--fo+TDdOfBDPb{`R-&SIwcw4#P@^)2V7V^myz#tzTf{B8M;}^x}WA!y&Me!5DHWh7+Q8aZtEVGT_y;(;N zSX)N2dBD{;FE<{#+L+X4*@Yl&eu52!UipakP7?*P#{2!;Lr1E9?bYluU^Czy0G+_&wOTTi{r-x;f#)A(&_^FKz<|)rU`|P8S zK7^D&XwacYzQL+$!jP7*;3aFp&mH6UY9qHe@=OjXC^y3bUYO|syyB^+o`UysC@JV{ zY~*Xe+p(f%BT*%##gB>y$Ch~qrPo(1DMA>r+#|l<+3Axm&~~d;ZI*S2_KWj@t?a!V zepNV1TUF#p?``k>=5PKcbnUb ztPVL}X_Dtx)KivedAHG}@~LAJTXlnTGq9lYaO3l$W5dCmYy}>*`gR}OGe=zMBAQfT z*04RMREJ_?g!2!tJTQKmBRD;N&Mf8Vki=&h3M-0t1zu&jhPl8oP-$l7d$S?*hfUnP zTr?#upFNH?j?BKLz8$>S@wYL)9DNAKtDUUHN5qsLXTfM4XN9=hb83RFbMx1u@b>sm z9nd-s>!XWQfSP_Ww`=ip(s4e0|4)7}%ZEv~t0w!vw4QwOFMFd=Gi~nf?Eb;O`vXuB zb%tqG!+|eE^nnk20Myif|9^e*`RAX9ZSU^(7Kk{#!4N%Qxob5$%d4vh#?xw@IDxr^ z@Px${2A6~QwYs{>vQ(RDkRo*0cfR`{{`gO>UcJhLGMbEisq_NWQw!p}%?UKi5H`UC z4PTQ!RqQZo3fgZ%E(dS?;p*9zG+asjHf5yqhYe zVtg+Zs|t~dB7`N@<(LavOK zG%0vHA%izuG?}6xg1QQ3k6SiZbKj9p@X53I7M5hJx?B}6e(5QXfC*uHr6VF5!x}G( zwReXW87cydMUiQItYX&z$tEN>z-MX_*UarW%P@JVku=73+(?liEC8Xpo zgw@3=$~-SVbIC|bv+`A)>C=+e4ReHC0orex5FqdUdt1Xnk6{mNJ_U9C^Pm0vnFk(# zmD24j@I(|2jZ+MVs6uff@=2jl zXCH0eytdS7_Yd|P#x+_Q#ys2B?~_LfU?wWD<0;GgTM8YWCtl};RGeRS*Afq#`sgI`O0pxHY9_N#V%TY{ zO6de4po1vs3uWq3bq_)r6`VD^e{p^teK;B`Lv?@?HjIuJ+bUuW*gWBLwM88;dK; zdwYA2KJ@6$&dx$-@#4jcnhZ&7(;5(>r=ba4Xrm1=M>m?~&=pcx?35Z5Ox{r;2-?#o zRIoQ8#BnT5?MfZkhVU*&^Js$(LA@ZxtdVEt7Hwf69LAES0|N{z3`ke|9A?892W-Ak zlo{mM;uqkVs)rXAB8fkoDNi_`b7|Oj$AJ~J!&(kbBBwjCDK62=Q_gf=B)%EE4Do4* zJI+O_csl51!G}otjF+ESISjfWB2mK*V=x6iw9isS1I@$D)WU4slz1XKlr+_b$!r2^Z&$j3ZvP z;E01Uy7jEc%Q!DS|AB^r$008XG=S=9B`E_eiSa%k*pgTTbR6r>==9}Sg>fkOCc4Gv zw9`*fp)4OE$%<|%Njh>~tB43SXK`}{18zUJzW!iXFB4<^6 zA-Rc-|6X?$NXHL(```Td-abuLHBVU!BH6~Tn)e}i#wWI>BD8Vy-C>~#*wB~s@M(NZnr_HW^e+ya!OFFMN~LPoH=9zAeqnlARKl+h1@nb z>ue3mRe8n)@Lmyxp)JsIOet_z-V%nISlfJ)kIazB+|HE_PxcFu9-goZ zJtIVyBr5Q0Be$fGX{1Azs;LZ}uDY{=h1Hc}R&}_-qsnAg`Li~#?AMAdyDqAx>moC} z4)u!Tagg=K&rhmI%Y4RTInG;qGMM6CkT%rZ(PAIsUzsfP3B`QcTyVS@YFh_9XQk9^ zmvwa{U6e4)lNh^y;}GcBM%>~9zW8^FVWK-jdzuPCVYDTewF22|A$ zqh#;iy~~h#hKfR9S+?PnR~-3}Gae8{%nnv}zjq(IX+7@u?4c=FR>&=~hj?X}J;UM* zS1bfO4xaQc0%;O!J+-cq&)ImFNzqKPZSgzGnX)k!#ih5gLg5GF!E)JTv?I6+MYQ_Ox`R4#x(DO(k^0( zrEmZx>bJJS!&&3dW#)^20wX&K&EVeWRjeqSEEq{m2u_yU$5exm-^++8;>(RYB@T95 zbvuV--O!jBU28y@9)7E zU{=u0>({SuZ*QMGahkI>2#iy4D!vX#5U`qvNLYX-PDMuiBovsfcQc46)|V{u==8jS zs_;`#YgNd`bS^0B43tHo{XWe*42T~Ip;9)fxcIk-`-yki2b1bL^Yg}YJ?AHWi!?wY zQ{wi-pD`(_h}z{>6&mVyy{HA@42^)R@AzSmY5a|=t{1j7f`>U{d? zr`ra#+5X@@te=gwmGO9b@%bwlB-2E#b#46^=%~jw(4Bkb+SPyc+yDCJt?OsboVkAE zCM=}0XV1RpJ?|ZiCcNE(LJNB#D%HIM__Dsf{_w*OcUtYWwKY(EuU)&wm5#4pzX^Z# z`+bmuLAv678V7|47g%N*769xWI?{rW&!(OQqmzceP)36%L0(NEh$iZ+WpKrs*HN*{ zC<42Rt}g>nX)7XgDQzJMo5-n=Deqw3%1+{lH$NHgO;TkMU~B-ja7raMJlp2dGpr(} zm`0dnDIzXsn5C!5itInD3a~H*L#e-tQr8kqrZDo>vB{OM)d5AwQc@wd*4J^V`+iNR zure$9*pN&c-!i+6$)NF-Z2pjz%da|U>3l}?C|7FrbLczXAyf#5i*=Z|g>l1JY$Z6{ zNltm-%6g{|6CrQgGO+Rr9UamJxlG_aBvU_rJ6{&0;eZMo!Km75kco=K!K7B8l0Gr! zKNwtLo)P;eNhSeytFY7YWSE%_D!1JxjLqq@XB*qwxxxwE-`YXi8%&fn1vH!G-4x8-PS?b-W#+djz%z2TOisW#w&e zc`GoVn>Vk2<};rGR& zSvDb?g#ov0$nta?QcUp$UhX5uj&gH0O^St{;x$Rhds?uRwOt(GHhHR07j(MPT|2w9 zzS{1>P)rkZFmaa+I-o|*z&uV3)&DWq}j=lw(-vsn>fcVnI>w=>6I+ zI_LsBMOB7H=9&gO1w8@HbL-v?!$d1G`d|oafiu%u!bQqx^RIc$YxsN2Z6raUGXC^G zVFY_9SIS#0*mt^l<2LL9MmH8)3#QosrT5CE7hqH9?cY0l<^<^3ZZez>4>qq~=`_;G zV826*wSkUG6w^Q>Whn!k^+X1@u)&b8UYcS1k4erXzH_vh5^r z5+r7rmm*hGsfpu~c{ebeJyo#xi072|FJC!URlR(&&=BgZ(Rkp22MVgEHJ(mb`(^$a zTR&&Hy^89_3EStYJYnRWa}|w+H(;_*5KAGoC(#sSM0}qvBc+}B75iHVzN(v`qNK7`6L!-Xtdi4 z9pIuc0twaQ1v(U4Bvt^%B(5=n7g$PU^$Ir2IX<#Oc`qe;$Wz*zVK%fS`voI*YmA4| z-W5!iW$zQCmb2HFcuvISoZ<>@DJDSsj9jWjj_>5;;zSp@GNA}nX+0CGxZpf%FCj56 zOt4~w=rI1I%%BU&drYo*K(3Ar;zA^~bhDVNcrplDw+dmv!4S+l%TdZLE;Sg+5R5P@ zbH{su3TnJiPJCJI#<>>N*~@0{5{crl8)fmn=+kPAtZjU=oecqqMOaw126L|qSyS?Z ztWd>hgkGMk>!_8(mW}c6b*yYt$|0Zd#KVSWPv@2CoAEjvF%GrMYE%)QocB{Pa|T#_ z;M#{=8N9wUgPvw8m_FZkhm23n^gO#F_;~3PH2anq;^BLB2zW%TNr$x`T>)SH>Q_Ml z2DaWoc;@uP`WjsQ&_fS_jInrP9nOpq`Sa&Nqy}N@D}VhT;a+&r-Me==K(y28a&{JH`KlnE+GyFt zpHY0dXN95w*E;FfS{$?E1sdXUM^2SHBuh{Qfl2F1PNoXMu`J@(&O28Uhp)Rwt*{=1 zLx&b=uB!>+KEmEoz6?8RWJh_?wH@y(wUf~oCITDI=@6<{ZUF3XX3vIrfccOqi1T&j zP*t+i!TG>P?A@K)`1k@5vguuBmYU<|6UyFN> z-&>_OEz?c$&Lt7XVihX}Dy($$I+Ew}g%@4`O$D@HH#h*L!e$vvK&RajLxv1E25xBY zoOhuR!t5SgV;y355D!({k@$A;SF0d5IDelM?9Ub!aq z>lY|+M2EJ>CEvifxFJ5H-GmJq0eh(gg@yaDQmO8Ed{r&ajrFd~M z00#78GMzAp7ZoP#VlBOPdi?nD4%HOc+1Y`6g-*zlg%uQ7=!fM1SHfkanH2Gg6L}QY zYfU!d!pV+?cQPq_t-f%$ki4pb=*B1>N|gpyfp}4ovDFYt2!)B__X`&;Y;0_R`~ze7f%m$3LDyG41#)MFiWook`K`B?OU6e+HkN>adrnX#q15%^CHfuJ!LkK zHxnm36ucREbRgpsbI`CKCmTzz!`@NOqw%RLJdDir{1S+BabtOrqU{`8|3ue4?1=5- zLiVy37c+>mObJC5viqeRbaB}ZM#A@Bk~q-J#~;a(_vdvfEeHuQ2eVN$nY?Rm+h%pt z7wy8VwqIjA(vrhoT03MT=09ik-q^gZ!qTq2{pc>t3IOp>hid7uQ>1dnsdDd(UK&Zr zDjI~jO`7+%mn0;=d>Zq29`>l1lKKC`Uj5SF`;wY;`0=-S*I@(xvc~OYz3Xp(&D^_Q z;*ID5hVjBOp@YFgC!YW@rFVC~quXh_-E6f`Z0UBVJNL)?z5Z}C98c0_W50jUY+-p4 zOyRQ@6Y5{ZFiKV5U&0M+|2`RR&3gGqpe;;Q%TfRgR@)P{@)d-o#89 zQ>YXb=P*9Ym$OY2fhxk5PSO~M14SK=zjGZPiBV*tzfsRl!9!NJ6U7UEx5Jn8= zEtB29s=SHXN-WYpN`B)%CEQwkv$Ac(`(msUszcUW{8$^|n#BA<&cwa*!&m}}mfMVQ z_L%#KdQ*G2Y~idS=iy*YSVgu^_#%;$EMM|;u(&CY4f33>y~{78fO3?0AY~=OsK|dF zrl?+UvYgyFtSIh+I)o7r73GC3bTRGq_SR3Hf>(j82EFYMdZY2+_~JUM|I z90an(#f8ymaAIkFJU&=lLT%@=CFk)7v+h7oK6&yad?Mca(xQJ0C@~XQ-7ZTT1TF+* znTF}3UZ})`0?{0I5SxBfb$fQC4MI;rYJBRcr_P-_i^XrI(-UXU-oAW5iCq}$3!}tr zVHCv@BcBPyU@8UuDg|20ff5m%kD6Q_8#q`96B)e-Wx8BgY>whZy&qWdUd}3SL5`Qm z;Ko5ImgO^&AYnT8_gkHGcQ=0^T{L(0AKf@r+}c~%8Kz@bOpA0}++S?0EG+JghM*!s z>pJcBgw;8;D1__`COqRYAw)Q4@&naZmMvT}&ZmyccaJCIAOrCdAcYNc0_{k_Z!AWd z)cUBC6!DFq6VoEkniLjMP!4U1+BJLFDECk(h&V!dd>E{dHL}TQ zytB0p&sl7>R~DBJ_V(cuDCNY76VNcA1mZg;1L|VN?y&SQ^c^0n@I9dY>RwNs-e}$5 z8Gz=D2-~d|sI{<5Ar@nj?M-rc+hjb|#8LAcqf&vF!h>Pc0o}gUYJ)1mXc3wbo*f4q zAxVIu9gBuR8n(`0K~o*{H|EJ=l&RUU@h6jMQ7^r@gt(K+8Im{RmOjVKkYhF$WMS0C zW26M=U;-MNb;p)gp_?zf@B(bdzA*%54G%~&L%F#Kz*bQ9Wy5EW<7PL_r@X@=#ZQTz zO_CQ>N7s57g*ZyWw=6Q}dJI(xdUUiXU~l5(2@|KNgcWLlVc~d7fk{OBjaOxAydp%% zwK_OH@oqv_rqD{FBwq^1mJCEk1_j}YbntSZi8F-?CE&O*W=yH!=+>wJb!Nw3tnt(-8p;q?9H2-Fzl1*2tCeOGS0_~orS`ILTl1?Hl9ox z3(aM-qJiFa5|^sQwUxaaH?~K`BWE_Yx3_T|wB8+I7uLEA@Qg8KXld8VORXWqT8q8rC_B2(l%`XcUr}DI2%*sx^l=(sL3D3$R)&wlZJwT1Y~@RnK{x zt?fu$W0n#S@%P3<@yph+qHu*Z=5`{^-Vy8;-#M$s!J4+U>T; zm+^ikOWjnxI>wk#QI@+$pWn+7s~@pd&k}Z=n(?fv$Us$NQdREheZRaFxln460jR`x z2M6OkXYCe#wwgSuvGyB3pT7vB2#Br*l!$m$N*-mQqOEsg$)L4A2VI|KZG82_j&uH=-iJ(H9 zc5JkkeyIrFsW$uZpW^?K=*q|jj|YzopBIzA5IkQK`_*gjI!s~^Dl%BdYs@}dPIsJ6 zCalZ@Egg(Tu$J%d?yaw{zw(g_pg$a3zw_lUe|a%Y3Bny6Yc@r54lMu8&CPr=U^?W& zN_4FFRoLC9Slt!oQ4>iE4RyxhU?zXPZjng4z$P z6^3Gn2-)MFLTqO^)9+7B3qA9Wm_VAKXSkD=AXrwH$>$O$f>f0Fl?$Cc7!L6B;9xKq zVK}*S(}_zEFA7y+_@ujvNoJD{e8rJGRYL38OU3ISK}b z4&J$Qr`JDVUI*=mcfm_L&5kHhORXlSP>MLHDLit5$23PzygGL57^sAByy6wFSX%DF zUNf}A9->zqu(KN9>kQ>&Qeen<#Lr}oiez98rBZ2g%vFRTKnr<&v8&TWDGV-FcU?Jp z{`s7XtC^5u0;ZMANd(T+QZ`_Gpv^!Juug$*!zexR#1oG{{y1!@3=)nST0Z9IOGW4@ zHHqtQcRC&13yhLDl$00|7buGNI3G$nbA*$nX2q5-e%cxxu$jQCF@LJxXUsV<@YU8- zJjkqTg{`67Lz4iqtz^@2rD7AesI#jb~`oDJV z8eDkw@|BN#?#9-#lPKlRlw z{MA<*Sh5j&y40$(O;u$l4D-fvHCf&;;+xV#To?&-ds{*Xk4?<7e8S-P5g-|$RFim} zGR~y1%b5NT({RXia+DufM^niZnr^YO48(H(i|(W6uw|G6!k+w!?n|8i#}2nCf_2Yy&@`fM{^%8(u{lFhwF zz1V=%j`A9BNP5vb{vI8Hqkex6O1ieber#i7xq&9nFMQ>%K~Ub=+JepO$KU?0rcV0( z{YJCBws9PTf`$_kue0^l^~G+B0(%ZH|EJNsa_REtKlcTA9LTb8{?@Hq7_>H-f^3ad ze>2r;WfFLXaLtzL=&|+Pn`r|?hbKGq$M`jjOkQ(tt+z&pF*jyj^7`RN%(+}?ZK6j- ztI`BxCyUSFjTOWxpLr6k({QuTg~P3#+^v=)jnSZuEw&U^M_UbL#bB+YCKme*sxSK< zc`HH)N5Zo4uRxKoA`pDWR$! z*LWD^Q`{qAUc6QoYt*xkjl?8X*4b;zbpd6y|r8B8t=Lou362PSdo3v8sh zg7;2}d<-g2qFjb#IW6q??yZ~8eCz2&o4n>#Pu%#%)1WS4j+jx+6w$A;j-OZq9cioKYo6gFY$Y;HM%Y$;Zm}Quh%HdW7a8H$Ixdtck$5gDe`i7w z7jB6W5F^B*EvO`M^j-#+Weah5LzcjVWaqjoi&OWN=f49_zMP|;&?Mo$*Tm7=$2zkv zPt4FNGs(?(q?v>aTUC4^czOelZ?1gRF5tHe95@XjyGU}DQn082RBhF?77Xie7!Exi zJ1Q66T1bHTfUb4w)T!0g)ii*0B~|F`cotkljocFD(R4}t*QFHB=*@=n!9jK(qIN$T z4Kk4av#irtwUcpgFapBbyT8-hyPr-6!-L($wbjBF2}Sm#2v!Ss7Wo8+b0JeFjvoWX z16sCzY&FsD&hCBCE(lAaM@hd_&4m!|3Wr|1+*t|D<*qr3YZc{zT=fiQ>Q`SaJOqCz zJb+tnr`8m%z~!7|sZf_KsH(ixs>&0Bz{eglG7g%En0=j0d8WKY5i7oUO8bsqJgATyk% z{F>@Av5W}qyavXI%?VpHC^8F{Un@&jPo9A1+`qqf@!98Kgi+b+v_ap7lQ72|fnVg6 zkmi!DSr?BIt+>+2qNCj4Fi@VQS2o|kOXDZ_$S^i8E8jQzPAwrr4B>VYb4Kn-7EjNx zoT&GFm*c`MRNM##v(suLL8jSr7oR^E^kI!|-rj_NNN-%6)$bG@fDLDJKOsEADX_Ti z>hju&jd#8GJ^#(t*3R9nKmYST|Jv7{YAs>(K0=LpivcYrDqcwL0DlvynJBH< z3xq20PhTIqbUQ1eKzCUE8GnKCvZI{fz1x-*mILCG--ApHNTF1G?_o`ik2$9HP<;0# zK4DHL4zb%1{hRwUior=rAZX=>hZmtbU;!K ztrs@Yn&28$v>t0rhN_awd*_V9+>XcGARe6A?=f}BLtcD-eT`yVzo~}+WQI)nBkb?h zWN=hdVi@RVNGUsj{lowHdR_kxjw7h+`|C)zwzjTayS8`x8nE1BYb&r*KJv&TAcpSj z>;NAJ@fTTnnt|AH=Hwaj2;p|Jvwiy;-}uIpPd*9T9%?zm?EnA}07*naRQoYDZ|_qv z#+1{~nsh8KBAZ}!&Q~`9K_TbGgRd7gK*^%zUCqV-@pxrWbwnNg9@}G_q-jy)n5wEh zp_z``Dte%e0zyK`bw1T#lrQ z2OB>y*5_jdn0?yZc$VZe+e+x94H(O?D)$F{={qc5ym7I^#kzT*H~|5~uV&LDvS7)G zsRDIk&>P>nbt`FPAi6P$b{5(adBvZ>Mnhq@VSSJwTb6jy0)JJOUG<#>y#+YT&6_v3 zx3>=t4zdgtGZ5|tk$eCCt}nz|^$1n=JRfvjN`CS1iY&;taB6oP=BJ~WbLUDhGtqmw zQ<7RaqZ%=GQPmaVt$LM~FbXj|VPRpRAWvPt-zQ}i*UQjiglc=`7+kP>aFC{hVXo5g z7_=80HyYf6Jis8N&Z|bq2+0G?QSs{=8@F%YzI*!?C-ZZJDy^oHSL9PF zZ-(!l$`q3_T$GNNNd$iZ>Kqox!{T*P|>nGu~W6QnDiCDOS-0Vd8LF+f7n zQpQ6AN)!o?94z5GckU>P;DGh_^wUqnK%GB-UMgl24G^s|I<$7Isx>IRpO+YnDl5;h ztpf#m+l7F(_@&qcDqm>tKt^acyjDEOr)t;TL}4#*J&6 zo10(y(wDySm9NAM!<*xgQw2H=qs42BhLq>JY(F8V6gtu^eURNu-C0@1;V-{eGBS3| zU?po;MvtE+ENFi2XE1TkiWb5UJra)X4mj1%UvcQcSxYY ztPJzA8XuEl+=kj4=RS5;kdO^7rsvsr#ZQpOx~dUD1;v&35x!gnYgnw})gN-mftRU@ z0cGwJ=H58>$s$e7KIbq75-;Z$ZLq)IdFtiFkvvaq?y=LE&+sQ+K(Utjh;n59eyPC! zKRMFzBp;3@qr#0wlVqI{3M(o3=Wo-x~)bAg3Ipx{r$az zdpo=RgCSGi`q~0NktFFdL=fvgOr}gSi7L%Oyk_yr@Jd73eN!JS8b@NdGMy??eZ7Z) z)+jn#btqoQTgXgTX=MkTQqOjomyyUw$|hrVYT|S$Z}~o)&lzomUz10d^7Byeq6>_- zhbfhjL_vxx0XQkLA|s|F2~#KW2-d! zeyCWmHfaLVt<6%}lX8@wl9aOY7*fknt>ciwrK-Gu?7q~<5GO1)^_aLCcvUQW2~!dN9!*~v(j16N3+s$|C};Ds=Y*v+ z_|tm49DfbR$Fe(}y+$I?SJlzFG^U~!%CF+bsC7-oHkLMY6l+(?%>n;O2?(lU`8#(> zhFZpS!q%D;*l?OMQW4&gPlo+otKDG?q;9tht=`|-USC_=?(MQ?RcA$~t%t+i;c(b! zqFym6@>Uzm4TARD>12~h4w^8${nV*5-R{zU?*Mcp7F7%75=uiAkv#zUR7Sq+HP!&h zfhI=-AD6qewe|Yfzn(AH-MQC-BWo0-2_S_h7#%&%VTKCcLGvP?-4Wy6?l5sdXoeHN znM6UBjUy3EHU7D_k0ue0T8;LqIdH+At=Tm|X+h!l-Mt>n!mUZ(=`QW|`|yy#A}TN~ zjbyo3jG;m8m33&`bPqZXTuB{Fk-Guy6bN|h$VcQzEGf&j5*I?Q#d%07Bm8#;E}(Ge zp>b*Ay3GtBo|YGpZ4D>;!-KqV%~orCFj_yp1`;_2$qxsZHar>;kJD6I6Y+^TT($^6 z(>z`*2GWR?>J6xWc|bu=KshWddEu0ll7}wfGo(&etjq;8>n#39~EHY)ISQ)@PSc_n^6l#n0ONk@X)LV{Y^0>mm z07oW|Kpmx;%?fjBuyT8Jpg43 z*9NNAh=$cMSh5a7_!UpqilU3p5G@;j$DK?EtnCXv%beT_6g<8c`-`bQbpd z1Eke{ANar?@Ixd-t+I5lm#;1)pd^n6D1)gSWCx=&BB4SG|02LVqC%r3sPyCEmjolf zE$i%@v}KB%O2hI@5x+t!3F{y*Zlu;o77`DY^=DKie@9p!Ir+43ORkwD_<(_h(yoV` zoG23rTa%lYaRi)4>?Xd78Tf~3ze%KCGio;rGKS(N;;3A1Lhw(^3wC|Vs(u@)v*sot}mGq9k_P~ z0I=E?Hg`u;kqo0l3`ohK$dXEnjAyi%xse~6;D?t>H7`C|v?a~3ylp~q0kcGYz6v_F zbca5VGTCU&!bYJaXv4Rhv&qV^k+^q$a;*u71H`z)uyF3K&xv7Vct)z%O|}5&OeI5Q zr>aZE2hF{$q|;Gr1F~^1fM#qpij-M<8TRocPgpvlhrO)G)c=f**_9|KXC*E&K2AYbD5*9yocD)Br?|ee}Y^Z+zn$7nfJj0&3D{pMCby^UrivhzDGi>XS1w2G{t#vQO01)cApNWfCeeqH>%2M05eRks*z30rE7~kmE3_ z*)3DP$WNm5@-AgUNzB*q>n!O z=tJku!S}CyVCg(r~!n?tH=4+ku7FvY3Y6MdmqfgQ{Vi0`i*aF_j)9n6UGv5*eb+xQqo7X z?)b&PT9OO|J)~Pj5KzrFmZj+|FCv#Ag33BAn1XRZRGMS2*H3K#=U-V_A;>61*gtxGQ3cAJe@-jasALkTVAOo%% zNSW^7-~j&Y_0WjGkw;@jd$ykBkZeeWcPgwh9T_kwY9ZVXV37kT)A>(xQ{5r%}xeC+1zt58zJ;UYa3~!2*|yP`ITpb zTCP_Sni_`mNE^P*C0pQ@OTaA+c!f@8X~so5iR_EUlx9<_D%UH2 z0b6n^IXG-&XK}!JSSjZAWeSh*8OBzCiFo|+$9XN^xpSwp*rj>&ot5Yk_!T#FG7oW% zcaQ;aW)&eXfUXOVdd;g|4WB^CfA(j8w%F=ixpH%{lbWz#Jj){F4o3)HNx2tPJX$&s zr|dyOX-7!3DyTp@fU%VTf6>s{5@Rw9CK(;HSJM1o`od1}rd55NP?QUf<(H*2zUaZL zc=jYpAg0vYT~)D^FJW8vjgO-Y+>CA71~?C$yrg19wL^x8xs!|P7#BrlQ7Z!GWD#ZV zR2C7G{cNYq3{G`4HFHF-_^hjXedEjgL@RG`kuz+vch%(o+DhcukhoRx(vB~#Nm+CY zqjPeP#su?3-v5HqsK*4D5Q{VkjkD%vomWte5% zczEYd)A#jp^ca3$AINQ2S67cMc3^W|B(bT$suLqF_8c0B1y3yIR50r8%7WB zbIhRQFSOy&HqYhe$t=yOjNCLEmm^NR8cDu6+Tn;N6y64nRrqqhC8IFMp>8H2y|6`z zzDL@;`m0Uy8~L)-~Q3$`P;Tebr{6rpCkvvOH~S zK}T|zd=X&Ds(e#1Eeq1PPf??NqX>0P*zqeIJZ`G&e_@-c7>sA>KbHJNiDJr+`)DIn zFzHSyzCC$vCW^j@CXrI z2J+RdD>oa;{nh15{oQ*YtAQ4#&{#qQNU$qzsz&f{JUHl$2K~u&Qta;czWL2>eeeSx z&Qfi%rq-N=m>8WJE~|-2b{L7x0hu0=6@iE-6*C8sv39`|jQ{`;07*naRL?U4&HLgP zzW}50-S2)I+6iqgY>L&7T#*+O_y>K(FL|Lt3V;d|X$Xf_N9ya*^uxCkuB+!uY!qNK zhpI~IMO2ETHW4la!xu%IxkToqgj`+Dcvpy5705q=C8qIdX?GEHgS-0!iiL(1YVszM z+{V)C!otGFV)x|9lS6n+qM-8!(`onE3dX{aLNXc+$R-w&lgYax6{^xk27J4*fEk#k z*&_9imMSH-cemORcf-or+P}QB$I|Y|EgEO+uKc)z<>+}(=l)&gYhIh zwirjv#+$N+IXO>ojj-aR>#H&r$}LscHt1C&>pn%Tp!`p6U7(xsaA2o)I_QsveHbg4 zbOgB#=$g1TNmS-Rh3T43)t$SW(3fU|kQD70EjXhw&XuoFM}|C&z0VV0(ixNuOL5%> zDM%iGmsyYaoqzZh*REX~4@XnWDY~ROqJ4ABx%zYm1|XzK z!{>>Rwn~WhW51U*nw{m9XI{7jy?)pG-w&VXAAkIR`(J+N!mA&HyQeucyW?wj3y+vMa|lN$aYb#(Wq-iOboL(PsbQN!2;QfHcwY$ zm0hT9W(dQQ*9B{CHo!*eU|VtX9K!rvd{G$R0ZZ7o(TR2)_ecaeZ{Q2a#!Ad#%;gfc z;3lH&YK}CWQ+J*18iiMEv$5USw$a$O)7WO?#0iH zpPPtj8ipB9&sf(KV+2JQas+82GuUK51{Vkeab7^i z$THjiZy#^SdMiI!{sGBTlB~FjB>D|%_<1ls5I%q;M6E6!X2i2L_A95Th&;C&nBWy> z-dI};^0<-pt?HK@npKu zdYen7vckVs@hb0km-dqrJm#&>2b12{2_`r=6(Tr+bj@{J$LGKDVClQo= zA-u!Q8ajt1T(A%&8gAGZT#>^lW0OEjrbvi#^+%y(F#0jvR#!urLgYQ6p(ycbf)aEw z3g81~f3cRGAP&B8CFd~t#xWYiXR7!Y^<$0Z%u0?SWQWZ*tD`qt1xt;ma62%eiuY9z z;eoP&5H0?|NRr7YW$wq!tGY|B^}>*^0kuwTxQPQ92G2gYgZ>_6)?CptO*Ik`dAPdJ zO;*OaKZu-FQr^oc)jR%^Xz_fGwA;VhVBQMBIjD?qkU}X>x9f-i^Om3Y3uOBAu|D-L z-!K~%4g3Sh)O(xDIl$CV7db_~*kO9;j5D7K#-JmZ{22X}nw0Mvh)~Vs3X9u06m5P)8c};_2E4y!w*RziXiwpk`%6q!0*wCn?q{LQzte-Dem#99)3@xx=+^%FBR3H>oJfjeO>>tG3x|fUTqN{ zvdw(WGf_l84`CE-dMm4ugh&$jeym1)h95Ge&f1+DW1iQZl{k+l(-wYa9^;*+%V_;a zGN?ZS5jEY-m}>>cM4duwH9t$cv7YwcZsU>kdc?lXJ zut7PT95pk^2KnOOkJ>x1H0q4R+~hUL@GmNafv?(qzhcJeAwg3d^`xtwa;3`+PBo5Y z7Y`+lqE^$#Ma&Y=4fIYHiF3R&|D8D=sj-lru_9lRu#lOrSqm9Q2O!en2HvUz)@FM+ zIwdtnRQA-6RZJO5!;DYt?O5)V{%W~H5Nve&eLpsDl{@QJ=~h_r0o}D$naD6C!fZew zUY5M_LnCZK)^?k^*n&qt&-R%}42S(jqtE$2TU@hPLV>R9Rdau2f#(S{pq#DX_}jM; zMoAtj!o|lm_>rlA-u|RoY~Uu%EYhc# znjAuwW?A%vNWdCU*ypUVCe=^Is*wh6zPi&9BTucJc;A%BIb2RsrVwG9$YKx@z91KG z9!#v`cE8^b!nRt90$tYEVd?#adx(K>N5V4YMd_`Z&SS`m?*HetL`J8j|J6izIySuC z-;%E#>Up*#&s>FGGgp?&;=YFp1PMDVgv$k|21t}>2`}zv| zLIXdB$s4Y^3+*nvol*lBJNk7eIG&u0$qlMO+WA~j=M7+$ z6t?Y`ym62HZOhh$8Wv1g{#~)y^Q9nrQdYLq#ujaMe=&#paGcaYiFe(!iWQbTb*1W_og%y3Pkb8rfK4Q zLEf-U`xFi)Ke~g!cwk|8W2PM}%dWAa(V`74GOPI+;NG#mr2vA?a)IWUso})MKzTyG z^7NO;`@!XQP@2Au9xCzI<0`LmmBm1q!v#5lBfZ7MXfz~3zPnNrt3S2cLb&M95cK;a z_;zz2fB!x1mEf|E8hO6sPL0}7-VcwP9ihs7zKA#LI8J@9%O2r?X4rPk+qH4u>>i;!zX zi*X37dF7QqYHDHfC)5%f#xU8Uvx=4zayPKp@N_+GBb#=M#KlJBbNSU)qus+GB23`?<{(C1@vz*&D)Cs;UfkLDemSH0Gsa`-nstW_ zP}Bun+uj0#ccB-dEkOFAETF%o`gdezK()s;) z9rha`v{Rz%`2~m+vpqROSl+w?4gwgselDcV!=-BV7E4VEW<*A={s+)HNKp8mnEsf! zzyV&>=PvR1y$@bH-vc7P_ZT+7zzf!UTYX%w^{_{(H+gnCFU=5qecn!w5%D-{y^gEf zuiD^3k(@qG3bws~#T87fD!Zp*8SzLc(qqT?riuzLW0`%${JUFV_e0ajL701(} zl&<@%Yu@jV``zCy0WedmEar+`b4=$5ib8P%XlS-^0lT4xQ%d+IsO2=vHp_L{yq0uf zshoOp<{okx$JgJzMI2izJk}~c6c)A)IE1f>LnTtY5`;|Ljqf}sf<*C1h-}<#XkuV$1$}9}s&k$6 zX^~tJh_s`k(SPo;pw}o~&{pE; z?<=N{`4r{BaEtcG}_92UvoXBT3Xpn80u0Yjjy)Q!QjqVC5Pelzr$TJ6phdQv} zT;si`JFSQPVFu6`oZDCpV(4tM3p>Om{{JliQesmpQt9!ok6BW4hLM+tuM<*B`}E1O z@M0(U)8k=Q!ti;>WrE7BLU z&?>F8Q&g4})?(Zm4N{`Qt3@a?UlRmtx$8%EV9r1qf0LuHn0O;_p)nE?R)lrC@ z+iFDPeZ!sn(!HF@979dFimZ}q>=`uc=>EZSA$#5bwxhX zT-IO@iiSK1=kPQIU(yc}@JuD;6zabVNLcC+x{&u1Yb`PTAHdp20%acCQ@J3kWZs+( zVaxLG+qT*tdfvBUth?#p>=3!E+K98x!^+yah^xQ8Ec%!B4uc?tY>**xunTl}vh|^9 z5RbhR2|^>4gccw;h|zxHnVv6#+jJ&!nZ&TR?e$ITIIHgLLa@?3BbN54%|=j&xqMRy zOJ9g2uI95C@;0m!>nT$t8&XVRxKq!8$`S!=QoRNF|08?6lqvW~C#X8)ukJ}mo~lVN zs7DDy=|i&8WGdCz|7@(*MCPj&?G$q&eGX=*Kg2GbRfVG#IqXpJEw6MjwftIDA7L6~ z8C1$b6!RoM;lj09ku7Jcu!izaBhR4O(F?&`K(x*^;NoNfHMb4+JI2EDC}PZTt3f(> zei&8$4+`#2zhg1UUN6wo%+UET7f&hy0PoxPw*(RHKkbiu=iP4kP1*sv2J(hPra-m+ zpU&FuV*+2WEmZ<^;CD?>Q$rFeJ&^*!$L&FCf6@V9T6;fU{n=|e?#6)dqaH(Wa${K%0MY?qB0{#-l2nSwwo($1lR--}%|6$%SP*VCHy zP3va*>r!*qqRqeE>C;h|IC>;Pet13*e}vfk;*e~>SI6hmI*?)U7Box%!RY@A>GS>s zirsZve4f|r-)3mU(0cG!g23Y-=j$}bUTm4f2i*+5GaoHG66buKcX2=mcBP76r@!(+*;C=u;>*`z*$j%oZACGVC7 zR+`!g<25x(5&#pvPZCYw$5@PBo#qwM0Ei~DJmfZBv=M#0ih5pa7MciZ64T|s%m>Xp zF!b4i*jG7&*fmaJ{B~2tna}>=*XC!H$1fhbaEXS!>P%H^jT@(~ekc#q+Ck8W4 z<_tFOT81BQsnYw;|KG4Ga@|(a zh*?+Mo#g30GFRA#D#V@)Cvlti=w!z#SyBium3cX{K)E*;6MczJ_nL_ZwLn-tr*eYk z%XEH%y~?~I%TU{v;Jjf1F$qpF7v3Hs=uWXz459DObGK!AwqtoW4jT(3uhNg0-_~b` zQ-EKL=`6WIB0suGxT{4T4CQgEJR3$)Qpd+jMfFdg7+F}!yL*FgS}W$^j37a4^20)^%4(M3nSE)jK-IOkrEyAZa{r=>lcHSF`M7Sm1bh({)}Uyma~ zHdqU0;th;pjFFT{%?qawkAh~DD*)DpF<7ZpRl^U%X?NcerKcOBW{3m#%(jiokBut$N@T6b zC0B5x_t0HGlaEqC*GUlnPr|l4^J99Pr6@y69_}G88$)@_?NpYFyP{2nXx zLu^|;?#%>abG|>0LE`#rW;m_ub8{S~JD<1S8wB1P7~=>(cA##aCbj=Zx*gHs@d;lW37?;l!ws@+tQUomOOWNd`+NPm<8?@x za(ZGaU%sOuu=oOsz}?_8RP&CfALn9bq<#C-F1Z{etUt&>7U13wC0KRg2=QHijVtka zljA>xg^3B+xY}rXd?A5%ACSYA%5nHB9I9XM0!$rl^Jauab5;vsFCBKW5~w&fQeWD85?g?_RG zsYs-`cvSgO)jt(@M`uevZsVHiEoVP}4={{Z);`XjM@0pnU}9j|nYA_p zDu5&wRF8vulhU4HDOm-1a#=N!;hexr62ywJ3=7^w8rBmUWbxKL2@6{|0U1k?{MISS ziqUkdkHL!piSY_#WUZ7W41OdYGIu~EzXrvaQ{`D-&65wON!o-Wz@}5X{mxA4RXyo?*7O69o#zj+ z1XIJ4xY;Z6YcO)XUf%0eG9d?lQ<66{ZeffVYGR)P3@RcaQda~GXz2%f8`nsWQ_hRl zov#G{k*26&-DPQgCWq^&u)3giq_^Wxde%L5vre3&QZ}euxaaA~pB*=SaA)s0 z8axg}JL1;Mm0-neEPR^%14s0S*hqvevtOSKA}R6&JY8~dP*A?7K`pgmAZ`B+ z>fmDmzQDnXK=&9IzP_xn&LWsXoNJhTM+`um%GZMy?1i>Hi1KPKL|1uLqPvC$F-iTlaKx+ zm-}e?r$jnR&|gP>cl*a8gDn|?^nO(Gv3SKGit~)fzYp!>>!7OE?oVu&xK#D1Kg2%8 z5q%ppAEfiY&Z`1>y~t89n>K{+tjQ?@=@EDttmIYQ;vefi7npEeM=^hoX9gs1G3Rg5 zB%?Nnp`QpFh^*woD?8v@IV5JFrMn(9^yA(41kph&;b%G{7Yltrk$5YWJ33f?jt`G}~peAvlLZqza?EKKMs^t$s~8YUdLf z9>Eb!4&td>l-cf}$SAqPMMX*ffiHl}J>JSwzUK|F%=4lYJdekN@QFs|gx^e|H<}hnI`f!{Q$< z+XZAuJ?s7+#E9j4!rpiq@BSG7FV_6C_ejnHfxrJ>z;C{foBrCL`W}Z#$|c9X`y9Ue zUPyeE-Uy%%yOipr`}(w|Iy1w(Mkd)ffO%+Nlg3HIeXvzFYB64Oads15!CSjFsL0C*{RFsZQs$s zl-@p};Tf5t0>iZ2FrxmR*`5xv%b~B&cf(YG=`_zZ@5yfC^Me1bpfw{>O_w7$1r#;{ z-2lT!A45-1x65}k$dE{i!D}vVZ9OA>W~Lc6>g1)Yl=Bq>{~%u2gn0ue#JA56x$OfX zuXDY+S&w$rX%#|74AXMawWxN+-9$g^!Sn>Z1iE;<$39Q><}Dn1M`^XMQ4A?#Yl^>~ z8Hk~wXbYYecdqaMzXhDvsmJr6Mgjac(7A+F+da>~3w1x~DJ`k(YYKO?@c+O`do44o zXwZIT|DlSHA85OCjwczXF`X&|L75^B3QPvXx)WErhj&omT@(B2pIrRzu^;7 z4%+3JOm(Wu7a=tlTVixY3#j}vO6i3AewlWE@qE2p!5;IOw~G0fj(WU(UwgJzgUPhbQLUsDOfF ziSxflBpt-)vBITzUG$=ZOQeSJtz40R)IE(W6KTapTykeCMG+0C{0ux)(0^OXR}mJE z4Di~neGk8(%IM$uC3j79{^;B6FUTcO-bvp5-qZS7w!Ev4Y>qAVYe)^@1-DD3bRWsP zqzX%Nz=xIclY~Ne_@EBGCFJ{e7)zyj#B8iXHf}U#M^#eKQ)IGy&SrFlw^eQ~fP~3n)W?>JJa%n5oe5Wx+TI12a5RRpVhb*sW14(3VFo9DG1}$P zEm}$LXOmTym^I8rGRPra4^7wF0w){(3gE#BvU9*r!X3MXUe`t zEv$jOWr5|{=~s_tx;=jJ=dNSe-#;J%8CnhhSY#9Qa+urGJsXlV**G|wH?G~(T7+B5 z73BZbg0`IfRVJ@AHg5sNmm!h17wTej7gyRFr^rtsH5`X5ttEH}ONE5>jkdKf3fgR_ z-8@^#qNAJ{*Bs6?M^kVjD3o+2n=*f{O_ZG8H9wbLoTo6biFp5$se`~Zcr$qbA(-a- zs+lZR7)+p^Mq;H*#4$ObtoTw1p@(-ofbUIjzvUu2Utr;DS+`~5_TF#9se(S|*xP!H z@B4`H5MaZalAJsTGE_Z3=ZTdEPYT177UxKl;TuD>X5uc&)@F3nCXiaWnBpavfyOz| zL$-#H+qjyft^?NjIkbFj%T}V2j0iQ})D{W1V?$P0krxHz)s5$Fr#+@kSc;29*mq`x zy6WdwGK=mGt4i-hq4MheZGX^U!~+cisKm}aySO07>Uw}9JxY?{+xiDST2su* zs_Q~%Ir0q$88<{5PmeV|#>Z1xmk|`jGGs%rCwA{o zm!DT-Lyrx>?dm4)AsS+;!6z$&lstMWDg-at-F@jXW5YqW3nY-sK2% zEH2hM!HVIs-xR)2{n~d!adX4gn=g4iA1peTHd>9Ji*vR>TRzA2zwUIfWWmqYp}=zZ4z+weWu>^?|1*vbLTTyrZ}P`h?i|9x5rUK&TGYg(kl0E zw?B-~`=&Rn`x)8UVCA~ck!;enU{On;-R|kF>1M7pnGCGb4bcXYCCKQuQ!AL>)e^js zJ*)OoO-ybQny-V-Xj5i>f476~SDXwHwRD>a_WVFL{P zE458|pp6`tL}L6e1wRo>nn0Lk(|xN!Nesx@5QfRfRQl&ie<SC+t+;Dn@7Z zgngLKc~y*aATsjHc+oIE2__3l0a78a?ENS)WE+SQH0x58B9$y^iquFntFZ9uymT`boMf#Qult{yAh~a3lGTGJQHCVQnvND0&_6tmCem~@ zs9NAMu=t4YqjK%VVH`t0VB=UwLjIU=5||*k#Y@_(B>En$71h9-=W1BH-aZT8pYRRh zRb{t_r^K?TI*MDYW_ni*K@PBq*qKR%U~tDr`nn}~(QV?SpUl#_%;aQeha&9tg_UwQ zKC<_Zl;=U(dJ@F(r0S9lcVUSiG#@Q8wWE=3TjmoA;h+Vm9tOF1^z3b@+ zhZtf}YEDE(K}4o)}4mz_l?0KR> zp{J^fQDscC8u+EzdLfDGdwH1?dXDqjig8UaSi(?Rg>$A&E85lfBhu{_GLnjypecpz zT;_ynIqVuF&H&k~QY>MR^rSL(Yc3P>A z#A`^}qq5>0hSd4C;WYhQDIybAQ{d}mUxD`)9JiAvi~r%H+4sD;>owXwAQO-kyy{;T z#Dz4b;*w0#c?s2<)% z0AE;%fevtJI;4b3KoedBxT#f$a2=A}b0K!?nVR!{-Azbwvu0frqG=im2lnybX)Wuc zNdK)UQ<~hAzu`>`OSjSKJqGx+g5ZX4*7ZCsy7pXd_x;%346s|@Oag;Kyby55<|H!b z2}FWc4V6T-6)yyv{*eVO{S3#FO#gE?o69Lmis}I*JuqwLvS)!63Dpu-pE(!%2$LjrS)H{Rn13>Yfn~OqMRH31)e}6 zHt_1uc`xD-r`isiEEgW4X?3U( z-w+1q%qoY2Po%}AeTMH)HK?bb@s6;YWa5oh|J6doDPD6jW~Svx)f2 z_2%m}9}t}x;vExUv??@birzIQhdax(zoA5-fycT)lN6KLq*f>_3l@Xo1OUHh(7j#< z`NJs?5gB`yf7VLw-}()<y0>8RU3dR30P9 zLKzA0(S`njsvKvvzSz4HMjgzWVxI9{;lk2$H_U!SxY({lQn6&bIB*3hiHoj*{+%Cf z41=VZDpt@U4k;RPqP-GJpF!G4&J~XsaqOgyxOEX2|EU=}+d%0WkkiW|uNI##4yZv%b!(UuBSw@Ve9qPKo!cC=x^!5s=O)M(C+%RvX$tDk z^H_XAE0WMNJsI2RpeeNb0sW}Qgg8laR_#0XI4+voRq=_;sx+g-QMJ=F2<$7c9H#gG zTL7>kohwd^KlGTcZ7m0j+B1`Q0`^K^R_;28vbr?oMKR$!8iAgA7Rexz-Hw0$kNfSn zO37;&#v!e!=RyX>Ll&a?m`2J#^;pR2m^QepW)*B$jr6$m!nw+fCeJCN0?16hXVhOx zLCuwKblY}7I2=V9jZZ$s!-f+Bz+iN(e@eP$Go9D<0_NW&C_1=uA6!NP>jr(^s+s5 z^`I{|i|YCz9H7y1-gBU^ znKkQlnUB>Kz%%pD4><1nxa$RDAmj!HlDpnUNJ~ip27Y(&HW7XwV*+}$<{aUIP27!X zIF4x2s)SC05(t)kf2|wZr#cbg?98>=kfy>Nl3ge`F)@xC(|NS}}AE9H672^@8U*5&Hge>8%|W z_YItfq8ity$H6KbrTs)N-Ib;JcW+^S!f3*6w!AmvPhD3@Qo-Z`7x2Tw=UjTfK9Ko4 z4-KbAamB_x2w!mt)*x;w_@|6D&4^q1*qAYXAu`fz3$;2iY;z7xBqz7vHE2~oc)6qM zjqM7Q$FFD}%OMpPz9cE^_nHoCbQ|ME_cjuJB&nkxU}xU8o;Y5Ql_4_5Iycxb8Yq;6 z%gnnpGqeG}#(Sc^s&J+|VS`HWi#T?GjKusU@amf}T8V%%!0`@%U}vU%di8#g!51YP z%oTb9$^DXL`Wou0$>UypXMURhk+obAE$Yu{b*?4`5uuoSK7D0FM-+c0(QcC#g#><@ zkmO3P|1NiX+#&knQT;nkiI>xNs5swf(4j3`#m_h!NR&aUk-ky!P~mrzX7u70|E>@o z#*LNTxnT3*wC%bUN1Spmbj2h*Q+nQus>Au{m=&7#^5vsuPH{wk2c6*%Fs^l)(F$))?oN_O z!yIYmBu(WNRr5;mP>{Cq(U9)lD_|fPNu##v8nYzZA9rx4kkcIP!NDa&WNJyI%9#Uqfaq9D z{21)9x=^sz+-om?SSR}tf(R2)hI*&|XmZ*I*e$<3-AqXaOdw>0iE!@{IJ+=GPBB;8 zWcDBu=1X^T;I#m;3&-Gj#tf3^E9*jR9NgTkFKk!^W65oTgo2n*iUc@9>_YK9nUZ3! z4-HG^ZAY&r1tl`cedUh^I-$-HOPvc4hdXp0+unPGVxi@6l%YHVIw@m?RsY26!}|t> zfk*!DN6nuC+401p(H*msU`d%K02`k`Zuz6JGFzY(gC`i#{r%qUH;AFmv;?{`I$(Hz zGzp0Qx|sfgx9f749^}|?=%=kAc$+Zi2NT6;A+GHJI-5P8eh(6UDi!CzJTUeWH0DXo z*IA8!8|XYxenU0eZNU@Wtd``wE|l;urdxnHf=$35Al70wevB&kqH@0i(=OM*C#nxH zf#`ev?2B~6n9F}8ilyTKLdSGL)#KiM&(jS?=x-nlSE*w30KMs-Je`>x^m%iA^+9wY zRqcS--ABb*H2XF$@HsC--wK}nxi9dwZ+po$z5h|h&wT>Y=_ zuUnq&SHy{l{~Yl9DvrJn@2~qD;1bRG#05OvD)7zzfaQ0KRZDx-vX7|2sS)DaJY9z1 z(9xt3FA?SW<&j!?{c)(jRAO$(9;0Zr-gM61gCi#xcAr%D{^T+>xV{`ag&{Ks?Fb=? zGfADI;?JS7nn)RPi78%PPUJx;FD(nn{i4uj&18d~%* zDUa>yoXOoUVh|&lLtQFmIz?0_IznWvn!2V%67KBZL>Ceh-vgUVLJCo^Tc;gV&iMcb z0gsm#8w|#-lDpx_iau6aI(K zy(fQHHeHoB=Wy9!Gf6%EfWIhVUJcwWJ$Hp+n*sEMDlR#?7r+lb>X>1|RJV`Z(y>6h z>2gSLF5?i=UwI*->S|tP^RKTB_2S!T6tqEnCFgAH&5X1>N6{k_KeVf&KJx-_~EEC|ko+DJdl z=SZCtw6I5@a)yP^=P(J^faQB-vYG#JK^d1L2Yji?@7uRg!|d$))9UfWUC;G()OgtMV%V2%8d6l2@%jqb70N3UFMx2n^4k@&_~royB%cmOfiZmpu_kt- z?8a><#IZG!VuB#~lny4PCqnu>oewnfT&9eFca!0VOFp@xU;)ULoxg{|89MR$g>jys zNf%bjm=jp0uCb8F`nas=aENYkQ)Q9S{rQX+)F4|@P!Y>Ym+=8x(-Gn>+@Bzjs`-&n z-2vj3*=1o+t+u0}R0YFv-7V)2!|T+3O^7kHj* z-gc@cPmj?0zd~3VycXvKCDs!)tv`wN|XShcUcp0!^kRHKGxl$l}^n@FU}G}RLnVW^e(WW0{k z`w2q$tqVP4a*YGIl7>ehpV>a2CZs`}Av`41?H&6QP8;?ZO1E%^{wKj;5_W>aSHGJo zwx_$eid5{cB&s3AygsKSrzV4E%SLZ$QeorQ3S@(@Xo-QQ(d5#*T%=^>VlD`yURsxd zl5E8GCBa?|>mSyIyB7=Mc}x9|=jIIEA9E4}pL)q!6i2mdy!Mhss-gVAJEZJ8Oxng~ z*P=zcyrGPVMaVBQIbu@DeBbOfI$aITuTiAU&r=1zHZhnpr9Tc!^r;YRh^eK?p5eZH zCPX(ZdLQTPJm*M*3IUPm$2JGWtn^=%uqicUqcsjg4tM>yQPff7y9Z%oc9*IuZIup$ zrne8=ccxBfJB)|gk2GC$8JMZAlT%ZmF@X^f*sbQ%1pXqEW*OUv4)IONPEIA$T;`NJ z93nsVcQW)pARfvgWTC(N$~1K}e23Z8b^ZFA;6HZUFSx!xz7PGrVjE{p{XQP`2@PsH zJ-*+!zk88<8LNrejA4)|&;*GLSh7`HzA63gC|l`BDoO$vdLUU+3q3)z554%`W@Gyl z{Li;ur`*PT-xu{iRmZrY-~pDTU|#+;g1Xn8&wB2U#Xr{#V5{3-b+H91(Gc15_#(nO zo97_tmK%OlC<0)=#%exbtqETJ!Q?`pm6~yR7XfO!MH7U1U^61c#DwoF!|p->sr|~` zU+3NQ?V#b8F3Y-Z^Ku-$&prE`EjUNJIBl#&$H7Y)+pu`MXgM$7P})_R4UqTD^lrcs zj1k~q1_2l$zO^f?Akp`E@Oya%WXw_r{Z;JM=BDM_qP+PW7WlfapKKcs(zfq>OxCtD zltWD0^=oC=Prhln?A4>l z7-FNa7`IBz&oIFKm$9=*mro}-{qF$R)u`bul>mD0{L)6L{0{$WFf{Ut=+^W=lb1xI z=3j4E!!*0DBr#zc!UMma%_R-8GPNF-J~3;>6|!{OD0a{1eC1zDX%G0lvMI&+xHLfy#nS3=UQ3;14pX@n}L5zwL@*IL=8nX`txz zHIFMWuZ+#9vj_c9$15d)46*WJF&aUT>m4#zs>+o^5miA}B6w^2mk_a z%ZN$JJjYTZWtPQwTm3c=(9I{}yv=kVbq(Bs+Gx+FuIDxPzLZK8Wdxiku5Og1udSdx z56t1dqNc0O7vCzYUAM9wx)y5fxV$fPqG}utjS zq(PNrq8zQ$IA1O)+lpUt&rI%S(rxpYG+nHd3K%txdU8Tr);vNf@{ooM8ZyDXx+oDD zYJ*4eKcoK{FWh_X7vjmueWByDxo&AcVI5Co4%_8$Z1bo(S&^8R@btu{Cw$o7l;Uho1{2*~vG@GPThcdVtmG8#Wh+iNv zV{*8^-50i?y)ljCjbtrJ?ZY4>5FRY8Dk_Q^bu|;90f8k+ZjwB|=KEd7Ws`Zgk$RBK*ngT=~ zXjkm9gEse`?SM$xQjyTapIhX-p&DXAkkRYL?3NN&_6Qauf->wn%k zOB&dp{}^jbk69pDVrynvHB_>oV`0Q4n>-+r#g;`2OV<$P@bYq7w(nos|f zZHYn-e*?S&9MU_`1VGdW#SJZvA+Qd_tF5mG|2%#0yhwqQz3RyeTG*Uuq{LO89}hCr zs;ScK-eUiI$>Wx-sUvv2UY0g7aFfGE+n*Taxd&U_Nu_@G_+V!Eif6Z{s={SF$VMSr ze?@W{>XweO54L%fUSb;+{qi8WRRT6Yu&xE38%W1*<0?H0-v1hzrfNJugY(O2j3Sz0 zV64x>5UG%ETM)1#^pF_MHbEf@*S@OdJj zsd^&G!*b4*z;sdNtaHgjDr6a5(f<{z&nu$JTe0xkP;B6h;)L&qfer`5g=H))2GVz} z+2rHvxGa!x$5Qk>v2g%P6_*U5STzQ)#zW5 z6{X8us}C!wt-$J-J0$5>Wd z`BGLk_kjtrNyN?^3JKx1DZhv$RpJYp{ZTaO<5ZD)pn{*7{3@?0i^*CJ6Vd5(sD!m+ z%8bp7FLQ;tuX4@GAVzDX)+G7L8cy~G9|zr`?8B%=rLW>B#h{ja&`&9%D3|Oc@CaZz z_G7m}EV_tHz^FMEkFsvSW{t!ziG>5qB*Cg}nj)aeOx%FCay_2wZ@l4(tFE-94ObRd zw!hNjQKP&a6|%R+YG(tUBG!X55S9Lfl3}<3#12$h^vcJjDp{ZS5)2?V z4H3lQPXN7~eqFiHg2;F`RDPT{93Ori=x(()cG=+4-WV&Kk6~L#9khqOx(wKaP)a)t z8#ql&iys1G`$}852Q7B_m(#cjjFgnRH&k|>f z^OKac3B)7{qmzJP7RzM#ag1ukJS!>Qav$Tw_lNoj!JI0PPJB~^FRm(E#xkG8TfVn} z(LSVoHbB}Hu|@|Ozh$<=+2GH-_bT*GE_p;65Bn4LS#A*UDG7%|NlOXr^q2A$xyn=! zAN7)Jn6x~|*A?=6J)&ZeNs}YS3@I<0<-@-5_e|e&iqyhdTHbQY!3!p-%TZ;NUN)tz?pbbhbFgG^`YrVX<7^8ZA z0%rIfKk*YFRY0>Kl$+LOv^;1{$+|Im>P+2EwWrVqOp}*r)r^|an&|4QuLknI_oe5d z!KL}btYFG34jN9gj+gPaYdH=s6`!+b;y`*7uSo7faO!jRztvt>#R0(Zr6%Kmp@L*g zfhiyLP>REcu0xrRmN#TwS5Br>*7AoJmA3q`)nruktES z34ItNZ4+pe_2M^jE?=0^7F|p)NTe<-fvhaZ0wGd6+hzesIQhir#(2Yv#WExd<2IFS zE#<8l{9c)DzPPtzAJ2-4yTugAc^U1DoCq5@#D;S?dUNE8br%6I+$;BLPyJVG#E|aK zQm#wpx%7bKn4?T-<-^Vj=$I1fMlt$OA3V=i z<*){da5|`TR>QM-Yj1zb>&hX$`eFM}b{y2x;vRTlyS(l|RC9zT8rBXY^l$Wr1- zV_BNTb~4TYk`tk(R)v3stWb=xV^?3!yR3di7#qD=Dx?VKm1mjYx7*D;Z-ge9+$ZqM z$|+s!h#)PZoy`m1$*?CO6_R7fD$#JeDleEZ72{=cSz2t56Zv95Rv$~CMYTFi!Aif6 zs}qd@P;Xyvp(~bCt%B{Mz4Db0uw+c-odm~>&ofIQETaggRFux40$}(vx5I)9X*7{; zqeQ4U*`_N{K|)?uY9sC+p>LFz7b?7Ai;P8sQ^^&Hbb?Lf{YSY z>7M)~2tO zE(t*o`)1G$sR5!Ab7J?UWv53}@6#?2ra}Trj6s9g`xtj=W^@l2*>KRp8r!`_v(4?` zv|vqO3j}-1+V#4h)*GglbD}HFX~wBqC4TfgiS`M(JW-`@Q)^=QdTs%gWy2&_u{yi7 zfa$5a{TPs2y$;ao?BWve-R9KP!tvv^dJWJUG&;LseYcMZGqN;a?)Em!uH$?yeIOC_ z*5Xp9IW-A49C~#r9Smk>W}5BR+6^0W6J<6>8w+~o={(XlHuYAMBZVy6{)DTsw`+Kf z7222}Fn5$i3=%1+Kw-gh2D3eJ=rU#30C794?1#u3?i80qr~i{#<=VNCMc=bQX9aEJ zOE@8%^*vQcTGL^lM00eDHobn$qdUe%sk8I5S(yllri}zQ1En?ba4$D?8v1wvd z=k(I94c%6+XL@y=uG_ZpL}F?)lW{Naou04dd2jygbK6=iHN2v`Zn_z*Xw_4yHO%8d zzP>&&oZb55i_f;ECQrBP-8>(p0~^^^PW9k3o;@-nQ0?1@Y6Zs>keSv{w}M4Ea~ukC zjRBUzT3+hGJ{k03cO+RlsMp##jy{16d+N-Ysa6|qWAg}LER2HAP(v9dSkiL{pd-dM z@$AHUVs_@liDOvUL-QNZY&FcuC=uhVGmF4X$x286m z5sP!w)dkd$j7}|c1LP0utnSiRoT#RMG7k9i`1BEN9#0)eQRq2 z_zMK>VQ-kJ!NhcP@yuMaRkwZ8VyA%aEcrONa@1IgBBRp1wBMEAfPtryQ&gehJ14IX zd@)v=$T&JwIc{oQElk|~Lj(hbwwHxDU>>=wrYZ!IQ1-Q*8t?!B5CBO;K~xL3jr=6q zBK}h(gise;Y?6p#VU%HDNlQnRC!?%#EH(PZ5kOL_%{YOP

fTgtk=e8hb+V}dtB>ZhrDJ-i$+V9|60h|ImC5Yz z)iyd}Qt2lTB!yD-AD$J@J)CAz8CNF_+t0w<&%^g72)#VuWPf-w4}XH&An%Fu)1yjP zeX!9RT6ZTMTGwhxf=3pp$i`)15<9CK)!HPyfS;#a%n%lh4gj3IVo#r}udnlR=Z2Gv zMq|lpR?=6o8m)27euG$;MoyD@9{K*f(r6|YI+DX&cK43H7**`R^(SDL6jACbH+IvN(m{`1o1zT z_)AO0rAwDc;F4y0aB!?#Dgl(`!i89?BY22+CSxF zVR?Keo$m8~n_8)s6b+z*x^k|V(g1>~4O*&C@ohH1gsPTU3+kV5AQ%Gs>qt^qAucz18LA^|k%`dpxT}gGV>j zI5kf!%@TRYuf4zsWhzV~?L3Thi`~6FQYLQg>}+gpWdiYn22^rAiS{d3@726JkOHi* zXtfg2$qQQg=Pq8ldAv`nOpi`$%n^9*a#&)v#e8C**QKT9{=wmNGU^{6t#sR6k_BWf z-?>wcN4+!|j{5g@?_9jJO@y?6xHp;%84-f<Zv#FJh1}CA$3JOQFnEA?#0mV? zbtTE(z3O_{L*;+MtEA}@jq~#(E715Sg3*sKF>6P2kW9r(FoY>iAIh{;aS69j4K@PvLp2&oy zSu>RRkX#h0qzWKdv~Ui5+txYR|NHQd#^yT7u4o*_`AqrM(X$E)`EZ(daLoQTJnaE@ z*Unk#hl+Wo_uQ4I(^YxZc*DJUfAiGnykZ2-v_#=IoE_FQ#b7kieTTSfD@oC;u1z*> zUVxcMZoW-DrEl?XrdmV*mgU07*naR5VpusdgwH-fpqe0?kOO zh0$=_C@V|_CZ~z(ftq1Q(bkOg^I1AqGL&N)R-Dpwc8f_)HWG;*w#w3u0fa zzaM;r{(?$9*R>OLz(!O(J;6>(4Z@+8J&NHx#6ae7Jlua~#L+xvqE(I0)E_`u15Dz; z)jS4MRFze_iL-YRasc3QO?AQfKDyus?9cI6d(cW4I~Zr7sPMPVa|M?ccLcM7w~m=% zZhIY-k`BDNx%u?dPm^X+me-FC2FL|7CzpczBMBF{lmY`3m+HD#81blvIpHLM@{b$} zT3vUj%PCMJPV^wc8um(3ctYR^u%Ac*wRcH2Wf(L|F`Rv*g+DJtb0wS|YXApVkoWHy z0mh>NAi9s*QHL zY0?%ru9DPlDG+O+gquYN zj1^0RXGhip4e8vub1#4DlP|vb;;DtDH?P0bZt>Ls7iW#SO14?5Zga7KXpLcBaVezA#SHCspYW{@@RO_OqY$C!?2MdMRmh4?Qx57Z(>L8(^qh;;4*- zxeBp;dZlHe-=11p!sO5=&ph+Yg$ozfPjBD3bBFY>ciwsD@4oZ*zyJHczr4(`-?L}W za{X{{KU7vP>eZ_o8yn9*|2$33<;$1pf+X#Tif-M$K_}4T&~+9U85kch>25j@ z(W;C?KTWD~x7lU#3mqmMyeHf7+y-_yQVD1zr%#{WzfTJMy^XCc&U%O}!aVc#;OA~Z zWi`v@YWk@QX$DJ7)(+jm^Ai(%t197QFA_@g6Q4ra01N(P|GEX$bACTRq6Tl?tpum!ztd!$R=;@j)u!qdaN2nw|{e z2sq4^|I)rjt1zJAN2=|4JBsHgQ*Ot)(BYM>3L0Ip09@Fy1+vnWXW*sO!u3MRx&*Q1di1_v{lkb$FSxTSSIu(JfLx@YOzC@oh1qEqnfauiG`}b7M;uU)yX_$ zmeV$NrThGmS&-+1B*lCynZ{r|sWj3P!ZSmzHOmiAnh*#R*^!BE}KuTjc z<=Hz|25N2t7nO{*7w5L>uOknA?4KXjYRN?~1v)LccBF}1iu-qQJpfnrw&k&fzuDW! zc8n7#4^DX492us|<&fj50tVova{+G^C0E)WwFre6aGlr02vH>edUu!JHW z%GqTOt5}iz2>?A~ZzaQkdW9kRC~HLlyq#+* zBh=Z#TNL>x&_SJ8$=PNG)b5DFQHZ$QefJ=lc#hY1I!yeeBKHJ&c!Q20=$XK^Vfh4VI_xpjP|?OAtNY+!kM2c= z1S``*NZn3X;v4Dp>(?Wl{PkabbLaWHU--fo>2=#3sG%e| z$e|CYBaP^#)e>~`qr<3PC_ECEO z)vx~A#=_Fg!~4stE71PS9EKuO6r$_7WP!wr><^9VVvsJ1OIn?Uq%3J#xcaTzS=(5D z=A+NihPrw6`lO%5Qe7sktyKhS2@Vq+&^TSDYZ1BR?Z`F`Eo8cKN%XRbZJ32H*emgC8IYN&Yz!VnFIR_koIi~LnY@6Cv~zs8)ezr=JJcLy!?Ot-~T>sx4!w! zZ~ppMf1M0P_Or-A&p0?9&>J%QIl*!|O^hBM9d4akyL$D?bTF8Xhr@o{N#eFH2mOO9 zZx7cNdo8_v?%cUoKKar|KKA?{{^1|?N5jr!;rh)RM8n-y`_|5#t&R0NyZ4@a>~XSP zV`+nddJ59fIRU=kpNcNd`2`bF>iWnX-PyU7B+-Qn=bnE0H$U~MPtjBV@gM*3Yd^lc zwZ(yj(P;Xw|Ml;$udmTve)T{9Rm5X2UAjbs{gioPI{gG);ppgqWFE~JJtJB8oGX|y zzIT*%VapX|0iFyL_f`w2T09bKEvUGZe&M2IbDzT~E|jta0Q_wMyW&qoS+|MGQnk)j zq6D6bMcZ|zXtm5FEAHI6MIS%*7=zi0XN~a@oMsqge~FKuE+W;^A`5hh%nIbwaI*jy zKd8})qE@Ff$+9+4xG*>!Xda;%5GqMtfsBsyB{gygTy4p97NW0Pw=w1sRyA`@N6Bo;12(quSS z$;ln7#kB;vCaMY%wZmvo4&T_tbtPc|t_S-)pJ}zn@ad|YJFAlj3U#Z!FdR>Nt^-g5MV9rOl3Cc&DD@UMax z_z)oWag@e7$TxgIlD`e5fbg2O&|Du8oGH!A)KB$3IG2uY+xQWy+}pcDJfzjqlZk-3 zmc z5dDtj+B`6HAHVctV||HJLv)Cs;opEV5fy7ba&>*Jz+6q_nSaPv^^Dgkypd-+{z=hp z80bPwinQqTnphu-lDs+M^@vwJ{`li0{mB3(Rg*LjHh^R2{s??-D%gdImsnb&UWgZ= zhD1I`WLWyaXxn2@`jK+Fe<{pPrmQmb=RcmQp1e^NqaFHjB4%VF#)(EI23oF13>zD1 zq-NQwmC8#O8C5Z{yYK9!F0bKtK7SFu$zuCvsmXuJV(lmfA2uj@_ z#^VeiCH+G9b3%P$mUJ3~sDfQoDdlRu=+!pgukwEz4dNCJNpKWBqP-9q3;rmsV7=Y2 zOUx%*Rt_bVErIz?LpzNoh|Pwa#n!W(T#NO9!<~=Vsl4@u-UAP-{~6n93-Ml?UlIJ= z&9)46Cf3dU?M_hI!cW3;P!egR#TmB{*xG{0ggR>Nd_jq{!%;d3E;t`)#yyAe)~_@Q z=b~S(n9VahPRP+{zb`Lw^$rSgQRfd^-P_3|rId*gL#7LMyFH(Y2M7w^geelIG+-VX zJWQ@HCC7Y_>5KlH5VR2RrO;1Y_a;`%MAfFtN8^djZEbB4k2}hTf-_{0B8bvi9||+F zgv1|xE|Y(DxNq=?MTrVhCis<=75e<>{{GR?QDcUEnv5SO-g{DU7q@Txw`Gu+>YY&G z^ZJbsz+|6)q3UX5!>&*>Tu8gL4w?hHFWH2p;C^%Vd;b^{h-Oi&PVG*FdrKc|nKvZ? zXS9YwHU!;JP^=8*pU%I1`}W0)7tw%iV`J;`<+m zx*kXiYpFEmECvZ~tGwWf+;}R5}Y(9U9dPLp#wh_%M$5Wd5bifvV();}v$LJd&dC@C218nsXI3x!ZfGy{kvB1@=YBi;E3d|Tm8Rj) z^i%B-u)>X2&ePJvJwA5}G&G;afM*pO&}8g7OXDkOGRo(gJQhCRYAc?)mEJ~PBf+B@@LnFDnA%@E;MJGB>=#K2w{m11UN00N@xx~M8M)RSnPzy%&maQdLcEn7)@A_&8M8m z%GEv`S7MCfrNtGJJPTBs1tc?D1Z&1#kDx&fRZ)>+fjrmo8m8 zeflgholYBwd{|VgWKWbD_WN|h*!uafCYHUQn_=IvXg-vGMYwM4YWw$?zk z!|GsfTK-F`Q|4+g8q$L-EG=$sZhr0ypFex{Y-?e0F5Q5r3+uPfx zS60}2L3ZP0k`gD-s<*(k-^1xB8;#DLJM$NR@#p)4(SPw@{&O1jZ~x1G@y^>B9aP%p7S^QnDWJyT z49V(P$sHCic;&$VN!KTuXHl(9+-+}fuBS2QD(~OFzc}hGpF2li@n)2^G|GE6m8-W@ zHsx5^m{NrLPlFU0NxLf~QcEOFgg4HnNxM}55W}dD82k|$x({=J55oYCq{D#CCzAMB z8e6mif8|*vW>y1x_`AS2cqq%K4WBHDBzFC1MO$fOjT?qvzkB!o{rh>Dt*k9C zo>^a7?$V!&i#<}<4i0xutu5097Z(>eYH9$PR*J_vwuFYz0iq59F2xgNdx>zyzAN0D z8La)hglv=fuT*!;aA6bst-Bn*k`-|XM#^>(=K-ZjcdE^{6uN>5V?+peD_2rQVBfA2|nMfeTdT@=6HX?oe=e zNW5esz{{#|$v_Wn@4xrqDcoCnfL@ymp{+SFwY9RchJqKR^U?TN>8WhPDQiO3kB7m* zvVzu>h@#CKmixTMs@LlZT3kXzedEThf-DVVbD7Y9C z23gQVhoouHC(k_d%&AkS=+7Vi;}7=s_WgqDd71EuPr&1}v1uVi1sR}jl!xTi78QdN zFj9^Wv_)wyEf9jJ4@Knt)Bb5WhG2Vh*`ycm8u69Ql6I0nym071BEUvI(ST1ts!S3{ zTy2r4rJf4D+fYmfGw6Jr+QlkmQ#ta|6|jwQ25=d;fY?e1fb2sTLW9A1g0Ki><6v&K&aYoCaTW zs@oj$rLQK^!4mC-eUBx(OaTI(@|zawS|s_Lx$7!0GDr4Ng{ zpKz3}TuR1SWe#Igp|(m&Q;6jz+5^=%2oiY#NwZC>g9>xUS!88x{2xoBAlK=2d1>|h z`SV+wXSs=mtQ0D5ef6(@d@~btQngvF{Nm7)(A5Ue?&$1_=Q1un$7~B;7A)A8?A2V)1UtI=RWs2GJ|P5+&sLG zaOG$+k}~5dM+lvRmSevT>%~tI$#YaURm-G}^g?Io4j}CNUBl`olB^UORL=3mVzj~1 zpkmNt&sA05@2M3*!KJCA8T;W6f5-~%sZ(f{>sfzza_xe;3S`kT(NdCqNRLVL|K0C? z_sW$kWP%Qd$8Wv$*6QkV>C)p7?rX_F=~rYVOW-9P4*NXpl({ikt+Fr7&d$!O-}*cH zB^FUuR0y#UA#ev z3{IauO*BK4PnV?|5&hExddu_b)vL5>AN}Y@Y4DFd_Si4|(l34g``>@_%{S>XSFe(R ze0Oba@!syeD_7p3`5;>Q+3RnRz@uxPJ$tsh&;@m|>XvgmVzQGZ#Lv@{PjVXV(P1Bf z6#955hgI@|sDfh%m3@oke5|A2bRn(cy@*aWR92RH{eGX8i)fw(L(1#mnDf2qPjT~;^(QXCt2OvRXJkOQTiCi@$8xJd8r4VFU;TmSvrh2 z{K<}Q=>=j6ZoY*S18F^-p;Ar@3N-CyQU@2h@jLIlL%U5&xR|MZl8O8kiB|98?lllU zUeT|hMbw}Tl#_tivtf&rSsOqH$}S>!plXn>WwWl56L>aKT%G!!BR($8zruI|eF?f> z9901#YyT=qsHrb-^=v2mJLaGNb363RNU#mLE1r0+X*EeA5DyU$5B9NZ0ZjJ2UK-Y& zH`pHhd@v@JQXbW)F{*&Mnfh0JccOjb+axd6*H@&o9T5JJ2vapgbo2n8=AiwYw-+UT zY1$&W5JwE)fA8M?$s{ZCn)S=UhdC%bCpwsBXJFQ>ZJa#!3MU;EKXE)WRKOZ319Jzd zUEZs41z+01`}<#oi}LWywqa&J(&4rD@YM-N(@;Je11nt>81b3d!Rg@uG={fVA20x~ z_$fC9FM21 zge5TSgpG+`t` z8C&>ca_Keffup^dYQ2*3QCUTK#UvISLG3$0`We?jO`t7fgnuhEkbnRju`9Y{N2K4= zIH!yNWXNNTo$R4i=alcPkf;J9*`lb3({jZ5S>^!tE{frJWQWSgi7h`iTa#nW-3QQ{ zt6kET_@+fZ8E0{nwp-olB&UC!_ChOdvp^DKSUEyht`eIDD6iZOWIP&>rNpD;6r!3h zCknDs=Z?gmYywo0U%-JIp_2(F&)I!8ms_H>lKldNOw&w=s&pwn2P6@xKo#(*Cd&3} zVFQCxg?qh?t<&3Q&UF_S4+ni6ciZhwX(WDcA=V@0LCJ)G0l~qcbdX=2 z2pK|Nsfx$hL}JY;))8zTI(Bz=Nk<TiL`!+)>Kj;KD>{t3_mVyt})xy39RqlK4OU&we#Z z;xB#aOPkx<%!o$P?jladhvR8JwlbBycqy)*m)y;DBDEvl4A!n|jva$TTrZ>rR4e6L zO=4R{$2cu^v3KE1Ru?dg5kP}1YpWkjl%rwe?Fy#~+xkhYf^kttl6~?k{+zS{nz1`~ z?$C@q^VH*OYs)&QkUvSF=Fa9PIq|oD`?sVs{dfQU|3L3ome+3Hxc#eN{%0f=&~NGR zXkX+^j;J-mkVsL@N{>|Q&hi2;>r$un)KgDQ#zWF_X!7YgWI6xjCvTR^3!nVtC-?5$ z`}hCnpP$;~q<#7+>Wb;g-6VPbBhSA4iC-caL4#M)-})#p=jqxYgDl{m~!MgOCYL=Jdxt_OXBRPyPwb+pDj>`ufj)y1RSSZtHR1w7QD8 z%{RXB?Qi_Wx1W6e?3cg%<(FT6nP}3c+3SQzzq`yi*hv1TyAW+JbQfu0DD$C7CL5cE zcUJ;vsP(`UX>Ah{BAa7bF@Gs?$_&!TnUuj%QqB0iJ75b4kd8x9(MD?{dLEdsC?Y?HsJb#3mhYkSV z{1bWVrKOivXN+2>Q*klND~&=3yCUWQ0_sCMKKRv2N%F7xYE5zz5#4QWtVi)DHcqY53B*s>t1Dk4r@#Y|iq6J84rKgH`#cqZ zAP>U1HQhR3LSF9pPb}g|>Fg(in6t8olf>syg0A8MP8JnUbH2{f%KAq?_5$gjz2%l) z0$=Y|&5TyCqUE<-olcuvA_c8%YLX7a<_Yu-3;+NS07*naRA&;-p#>8;?!2Fst=`n; zk#iAFzJKr!w2JR_gmO7Nv`QJ`*64%%ey_JO7+jr<6>ti)K=XKYGJJK{tll(+A4W<& z4wecY)BPETKWSWCng+*$h}kCnq18^N87Gap9LcK2+r=TPS9wy)%OLfpQ|2v1a&*CS z=gvjZ?ft#uJU1QzUyxm@k%x+;D3%2>T^oWiIDfuDJNuK_(`G-BX)m-bv5Y)6p0PQg z5&W%iT#6l3f%9ST$Qvg?K&)djEl|CMX(!%=!lgJ+CqmW2Uu4en)P`MU7|s8Qp84E5 z5Sz+vgEE^U##u&@fWMH`=D5h}D(dY}48?7|B@!c@M+(&0p;|4(s<>+uPfVOACO`D$DDKdqdkR&}L@Z>nEPGAmJfR`6}E_eZrBz$kh&c z21j3!uAl|vGiL86trXX8sVNKqz}Sd>RX6CX8FM&$9AMPabvBA6*eDTWg}9;!T_e6{ zW6g<*$=ZZxbOWlSxT`u4V*pu*kqO2iPQq*R^SCOA)+(nJp_r2h!()JZQx-8{ zvNia*gbO5D0>eoK1QR~gdmhd%`u{ApfJZ}hE=Uv|ab*?6e5&<%wzboxhhcDey{axj zqo9j*6p5*$)TvXao_OL3HaLfDA#{5kffGPn~Exyt{v1tIJaKCD;dk_yliD1G%<(gsVq{^!rim{O0 z!%vpr@h#5SwCX zZn-91pF}%d1Pei5(fOnVkP=Vdj>j}1BymO;FLIgyokmJOeai&`=g!e5ufP5p-9o%4 zL|q(@?{*nwZD}=uDn`_c=c03H%tUx3hDjpOUQp=rJ>`=4$(Z3Sx^mED%B{yR{9Nu?5V0@RYO$!W%Zwn)2D#oXRo!$IJyYQ&6bYNoH;||WQr9U^VPXLtH!E9 z;y9N5rLAkGAq7IJiyWrfT>A9qgeNo@GIlOh6NE%{6<%xVK>qIj+Yie^_)x9`R7g~n zyK4qZ)>M&e(XH9&P2(_PPhb<#n%b76$aRv&Le>U;FVu+#T|ekLL8dQjkr|iqpFX{b zLVBWeqJH?uNOtrOk9^GN*QZR zi_93zOYiZk6a)F7(#mEP7)K%EKavYb;gwY$bWs0k?5tXIYkhrPIU1|fT<4hJ@tBI^ zg)B4|eHtHHi$aOZ-oO!QSEQkCJ^1*r2>X2>V?L&|lu6PGH$7soI2u8%(AWzN5tshKyyYPqe9_K`V=oI^wsX}E+R3uH=FFi*kQGVcL|@)1d#*!Iad-%+doKZDCgnB`e#ut5t81l$+5Gu zleC8m3nK9cSvU^~!c3(U;ED@OtE|X|<4HD-(@4-)S%2p)3*yNzDxNS-)_~QFwje;L zl=Vy90<@75KwtimB!wDOo7l9OR7OdoPa>UamBdkp_j1xn(iUf+(l5&nm!ZU|RL3Ub zbC#On*e(D?k7=4bYaGrYYEsVbR?4k9M2VGv>>l-BeyA2Gpq^d3KEVM+hv{%@Lc%GFrJ zMN}|Z(JM`G)uGhJF?20oMYdj43YWqD7w}tg_H!Lp&g7%2P%ym?hR34%$J^W6=g*%f z{&M^FO(OQ*VwV9X%eZt|YU7Ms)dMsV3DWeTBzf{;B{3&IXIUAtQOsoNkP_k<=$-Je zL?Ss9+~$Lu9lJ3r2Us<*|qRS||be42>W{7bS!xe2eGLck(faRI;1EfpvP&0nqSP=yQ76@3`N~&_@Bgp= z+y73V503lO@nmmzHz!jtN|YG(T+**4!f6EaTrrnBx-X^SnpMf=ZkH}L8XlcJd-leS z8>Bh!-rv7-XF4g>?YIBByUc>^a5yR$9G*099tO#R1xedW6YbZ!Vd_IS737GB77<`n z^g}XOfRlXd)-5d{RiwTTj`BC(xc04YeTyXPaM;)4eOg`Zk!5@3%FWSeJe3TXD9x|F zbN$-YcfawCZ_t?^mjm9VgM)oC{x{Y(3h86PBGW{W%2-n*L6B)mGLq=oJF4k`n>Dhf zA2HG{@KB(!SYGLAk_b^OeonzJC`tI!Qnku)mXDA2$26FaEcb34?dR{j`S#7LtJ_-) z8*~0lY~oy+r%zbUTBcIS)o6L75ZB`5iG&sY9|_??Q4RKT<*%))FUE1Uhh)E?eCK5k zTzI;c{_~+9Cm9=$YJ^N^zi`n++-bE(+})p>Tj}s_q1PFVax#q9mKL6T^2sM2KS#>q;zFm>O5Xa}Pnn=)x8%@gVh-iUq>o8B zQFtKubBxFpi?&CY_{e9qSY1Lx+hOo+vUE$=hq(~tB`c5{m@rxe{0A}n(I-W@dFJde zo6r_0r0g6>N=b+_6mnD`B+H#82FN-i13^2qVX@`d_V$U;vc6K#7imm%HTeRS(_?E;+%-jR%{lRq+e(f1ca%Z1 zlEQWIbh>)%(#>ic0=<`rZ6f^34$XL>EQnnJb1uWV0g|@Fy_jRLE}w{ili@ zip7CHNz9=ZW^0Qb`bDV`7lmV5oE-@%Ii<}>tX=aLaD>LT!hW%7Z^q(-Dcfh;fz#R3 zh!QwHvAIc_B)yr8Gv_;wN&Iow2?=goL4O4tV9w)7=bYef&HFse?1IA#KELrpVjOIByVL2a>im_T0(x z)Y|PFVj+?sXLHKK&49ayuffFF_f4vLz@c4m9!?r0rI2aCRo`v)NM)r}kFWu}Iv5Ka z7k+5sIo`f-u6|+r`C*i&FhCc%)~vopRJ&3QXh9;wq2)9TVCTlGM}Yk$-Ujw(hOhp#>LM;OMsqUGrWY?> zeCFAY&`3V}+0Wj+dlxR!!EnHr6*p=ok-Adh=_I&a-A$J+rs{`h_26I*yG+~eB$=-kguc)LVwO1d}#qzj$4kB1mjnPIidif6Par+ogx0`cc( zpMCb-ci$Zx9c^rHA08i(W%a<>&taP|nVcUpfj>kh6KRg<%$-&!i-umu$ zze@wYz{k1Mr%%89!plh4UteEmP&5IvK;ReTBz5c^z-5z!rf-ST`h%lz-vz6t)C_O& zo6CR20A_}>*<+JmyLN4IXO~uUeW6RYxN`FbEzO0kb*?;jq^?CW8P}avyIcEoeaQ9D zHDjD(#WZk3xon7*Qp+qJgzAhAu`<<6XdwepCE=NRmWQN_W*0m^Wu858aO`}Zzg zx|B_(Pe1*1DRCq^tjLKAdqyPAWHXX*=zuYm4Wo6vLl` z8ugHe=Lta!z|y~^abp2>m6&j30F!9|8`x_~k<^yYGDiF#{!;aI)LJ(vhc39iy{%PB zG~a5WNrN%Av$6Io9%_|x7|cl{PCL7vI!L8fmE3tBGiKj}S(7SY%TdrRMLyyeWC+vd zU0q$>*x2AoeiftV4r*NKTM|-t?%dhi-GzigNls%v^*n>(gB)_%W)L`ZcZP3DYxY;P zr^H61$D!w1TU(>2fB_5z65~X14RXiOsi;RYN&o;507*naQ~@@y3UnAzD?N;~%ag1t zp|2#Sf3){VRIjcrGJ`X6gE*6gO*4*&wX=LQog9ybWu!Zi%A=V7l@_>Vj4snOUSy2Yof?R0m0B8v1rh(gk`E(}eSE6j`O(TC8ay z@(7N}ToB^0x`^D$$&Or%1Q8in$s{G565IcVZ#i5FHy0MO52@aa!$Q2X(#swowYUkob)6aL)q>1;E6ms?B@k(!>vdV=}HH6 zpj?+M*H2qf@AZd+;bd_3>{;}8rIU#@ z(Y&!>$V6A*czJA%F}Vr4{*o|`Vp|CB)nP!au{SVTLG5sxjV z#Uv+9RCl^$>ZpY-Q!y+_@nq4%R{anK}x_KucRLq{YuaVPe-UE=s=QFc;TRV|F;1tG-n(o_5UQUax{wJZ4V$tFM8T{q)2J8m8C(G?c=?{$k}p`|aH z@xt^-XL`7}%)OSmBtm66@jfqWLTJIFmt0k@tDlaNSWq?uDu51yu5%bF4Uf-dFln;kMB zCdYj)gJp4mocyF@1WF0EDQ)a2nCll z!<;`iQBM{^Kc<(rev15zNy@;Z8NfdLuB^d^2Z@|6pq+ZDVyi1+HX?MgylDcky5K>4*i-oll!-b*jOva!B(?b zz(++)5TfyM4|dYuxkF63-CAN9*|HKMa&~GW=#eC_6}zz+RT7~q9a#(sdC0=M553c| zku&MS?STQTDg!vSlp!Ou$ZS#xsVg+*2(eika0&dE?~&pn+tDUb%c!i!)K(N%4iZGU zVF+2lAiq9tJm4f0 zaR|;hu`pfE8nm%ul1x4+KaQLFeMmVCP>w!Dj^E4H&`lD#w4cw7jBMZi4E(=E`~ExED|^0w0C+V29_S zT}>Kj5)nl`)5_A$q@zAmFhi5`>!kybaQ~!!(T*(KV-IM!3x)<1zNpuZja+EN1K^)3;~Op5;`@(O`FHrxmr!@i-FTWjK|Q zB!K?l1r2E3V!8E{f9;mzOxBA)5>(hE`>` zV6?W!co6$lbHuUnDCPLp^VLwIDG3Qe`QphhEov(nZ@1pP#bpjd9x83v&wlo^Wf75D zKb-c7t7DH#GEt2B&y{rsK=sifdJ4^9fLujvIu=N_tktenxkZWW6oh@SeA+rnPMqP! zdVRRd_kf$8r1NO!g;%orw5$gQ2mRym(a~@+k=$cpp=DIF27{kJvMr|+9F#~Muer3a zn>^^QaBtg=73fU?>PHh?AgUn_1OxS<>MBC38`JKkEpg+mtu6U_e>j{p&Y1|9xd%{~ zdq4nrd@O(SFajKo%a7{ek5D%Vm4tEzO(0}eP_SY96#{hEmxFc$i6{D&t*W$5@97h! z0jV_$wdjXA9+jR$$_(Qf;V0okK_Hec8wfdrBsXcaG=AFtB%Mi%qn~gRiX61Z$*`w4 zYinzg+rrF**wn03)!*8AEb-oQB$_ua4-sf|lF?gourQUB8E)MYN8*&pktuBi;{&Y| zp*bMWi;J;mrwmM_KRBX+3M!a@Dw85m!biyLX+k1?G>P)jaNO!9oHMzUu8=7#9{0$G zJDE60UFh&9Wu7pcGfY`AiN#pdQ7h7Iqk7Yf?BZ15j29vmy_ z$Q$d$u>D2Y#}dJ)Wwmo+@>nPt7rb`;b%%AzY!XRFihEiLA>eA6jJ zra`3;wtbQFm00^uR1}-4UXIy!D~YAP$R>nG2+9YA4I$P2yk(E_4U?os6YAh zBM%zvDlJ_SoSXp)48wyajU< zg)tUPnTtrtLhH20LVg!6TsVL6!mt1OuY+#@Gy*?_RSRFiM1ZDgYs!tpO`{k$rKMB) z#~}~?gc|~D4Rb=r2<3^dS~+K}7p2De<7@}uy4S`8>E#VFb9yje=hm%TqRLp82du16 zn|v>FHA$?e)A2w2;Jeq~y)qddlOO~hn#ponoz7y9wrVfs_IDk=Lz1=_L~S7OOY!20 z7VvGLAns3d@g|gJLKLX~)xY{5Y26Qx_Qe-_ok1Fh#~cMM7_{kl|1QHg6;oP^$+*9| zx=Obu>C$O0^7?jq5jRVd+SIhgYI;%S$y)@3g6W~ms>GGZ$<=BpqR`Q~Xk=AAU zeUd?0l&bMqjruIE==j7ZJ^|P&Y*iZ4OE10j{4ag%^5x6_@DKk$Rxz4y9UL5GBkp;S zO^cnK`{hU-Ps*Pi-FW-08$bHdkFXtRHqM+mLq8{>h*oD9Bt0?^*XWT?pFT}e{AX{z z!QF!=>;|Gq6TSzu67~qNdz3+%;qc{D9wZgTr0LTjr-Pg{wd36+%T~yo8H~GG(Vn)m zVwCE9(o2^%HloFacF`?b?NrAT=(Yy@hrPO7x|+lmdqO^D2YFEzb(2N~7O$$iV?v?| zDX{TXNW-vxxrLa5<4+7QEo6TJqQuYdc!1g$I)SOJ;xdo=0Pfym1@b zPCT~U9i1mD1fV*3d-v8O2{!GZJ!ONCl{*=a83md{oxe;v-`6Qv@KE7Vw6gi(iid?8 z7v6Sa5%hj_d6g*V+_`fkOo=TJ*TM{hF`L>L>VJ9@6;|rr-rjvVNbYmjw}k~I2{N6O zZEW^0xNe{{tEWz#qOa(7WTM}=af1{FwwA-pp91}LWS?NTC?`{{*v}6IPZdkVOy{X~ zIIH0dT3%@?lrZE8Kza4R-~QPE5oQ5V#f(g)vNW6mzcXdT7;I3ukJrHOJ4>zZrs0{o z@p+vPLV}PA8C|LDAO&whDQ9~asLlw}*|E*QOS%#c#P=k&P|dTayoOBDL5Q`S+o9Y# z>0M~uwXm9dW;m;=9@{6KlMQp|=W)z+zlDc4 z`=PAppl{>}C(jfFsu}@fw(+qyqEs-eWOmZFB-X~=8tp_QwvQ|_acVmEJXnlhj>dy{ zGt7Rdtwn*2X`H9uW)Q%6;kvfKL$4&;3YdhYwDgc<6$Zua4~~@Z5m>X_R3;k1L#ZTT zQXuS8e|<85{Y?6e?8(@V-zzT4F$6zasP728drNzBa}(8=%WJDdgfsx+MHs(Pk>4+v zb5CiJE27peRIUZ$#s3*OLN-qRBUS)p)X*)WXL?`H9^qZWwWisF0jyj!uaW9vT;ff* z-~DXxrDMBf;Pos_4BND^IFjHujoYk<7eP8h+_q9jB1I)|n2Gfx%a>GO#L{UpQ3{Ja zj)PRsP%zUf393lLj|u>2t=$* zQLcJR(cq|Tb=BfpmxvQ#*t2KP-n(}Xz~HoxXc({lcp_<#H_1-=IZ>Jtjt56I7M&i7&H*cf3PNufG)n;#pxTd+Wk7RK zu8kgUgkT+4E=jlQc4S>4(lhyp?aZw$S{mJ5RyLE+23`H43*`ikIbE}IL&~fxh%O-_ z2F;^94}LTh4}UoBT{Dlhh1qA+?rJNU_t?VW zH5(2@e_4NJB>lqr4S@q{h_4^uVNFnvV=)m7Sq#9JVYco)PKD!%Kz40M=E0&0<8NgR3Y*+{6T zv?=9U{i3M!VUC(WJR$6Jtt*lWnmp&GiU)cI z6*6|2bBqnYt&G*?J%T^vKTDF~GRbcl?||4oH@{itegs6@q4JONwLTAD3WH!EnX{{cb#ynTSfYA(Tw6gM7Agrte_PD@(OQkLQ}+j6Bz(ZT1BAc5O~GhM{B4MIUVZaw$ha~TLoaij(Hw7}&voZFI2x%ML)9?_p;tvIbk$6QsCChVa^rX&XmncRVY z&AXXYCCxQ@ZDkS{>7_R*UAmBbM%D%j#EuZrO^8M3g={l+ubVWI_$>{BqiiA`$|})O ztPrJayqA>;>sYrt6RNWWB+;|Z&UP&S1?CwH$P(#f*hS(6VLug*OT4JDU=P|rG&&Yb z4lGx+z^>v5vr~UTPPU1=D3sd6PB7}7csV)oDkkfBDoBa!uvCfMR7Y6ocye;Aus06fH79q#XuT+9>CP74_yXnw=hzek({vO?D9sZ(dqF3?l__{TpkrIw70 zqevQz5qS`q5^oV$RGzVh-R=iJt5ZfnSEN*Qwee^=857avANk00r%#{W+}M2l3C4Ok z+}o$weVanyd`~2?%k*B zwkO@Y)aNilk&{Z?63+`QH=X%k z|2Mz+_S)*5=C6;+t>2Nz#J(u(b0@BzGWJ ztQcjII}^7%Xy{OBA%(O&30?m)Xj0*B#Wdy_TiSp6r+-SH{D;5%u9SQaVH1Aud*35% z;4lC3FJF4;B_-K$M5Sc$(pTM9d+GFl& zxX8^OV(E@9QCZaG(_-eFWgz|AQ#H=Zyp;`$Y?MsDkCv9YDT&W)66Yq)r`f^% zVLlo3I!~S1Ixe~ERMu)0mTtA>K0&sy#Nk1(%c;A-9VSt>$0;*h5+I$BY9oQl{AiDfH*w6V z*F?tCNR^Knb zb^G0S-yM#}pZnbBe)XUIQ?}d3dD80MyLX@V+WGU3kwCn^zt4G+E6Z>a^PnxbTht1dnj?{442FW`QK;bCnlfOd?%HcjK3LL_xetB@6FSQRXKw9>t_Qhs zAs@s=z$@%;ql)=(%zkbJxQ4k?`X^=J2$qJG31lCn)G%Yb)g6wiF?&AB(pWhElPGY= zhV$c32*VZOIsPa0Fl^;5!bSWPH7?~&vpb75nW)MT%w*GH7mHeG8*s+jb_w!M+i(ex zg;#&lS`n5w0aJg4FfJ0FkC8{NdQteQ@}U$`Prwrz_X<_(QZiWS1Qdsdc}ch+Jc9^| z_~(jjazPcd@q<*(SBrs_0cH9WidiziC+N`026kHY_vI8hf%U;W8|T|abH^$IOm|Nc zYez|ckqlgqSt>q_1&}G9Di`g6TOtS6U%?NVCR`hkFffVDg2?hr?Ecas2uYhCBmT=U z2+WIGWWLPF8hEgtb*)1tzpBcoYo|Mi?f5ufinKC#tniE-tZx~B~ z^p)xpWdVMLMoa7;i$~3uw>6>x#x=%VR8-~HSUVrTZ*nCyFiEiRve_OO){W|2ALkw+ zUoe)1+52j3i#?prn+Gh-Ey+YHJ@vaiDO*b*!3u$W^O{*0qww3!``XIHBu4ijS#;u zcVY3F)J+vKIcW>Mf2}+#9L~OE zb31LDpo200HVn^#kGn`O^0l!efCX~)tV6Y?@i#RXaN zqWsO@{0&)vzx^+MONqJzGXtZDW!WTx<35s~>%$qlF{`99m?H_W@^U)ER6AULqzr(&DmPMBE zV34h>bbs`tAAv$%e);9keC9KBWg<(sBz!4S_p1+!L&hI?0>GTia`ChopQg4F}LHt~nDQJt`F8j`7 zlaSJu+AK~+a-ul2EaP0{0YNq^ zU*;W;Yybz8Uo+lJU^P{DR|)j$fIMO^*#Sr<;I;J;s3iaZ5CBO;K~&bq+Q_MlX41#P zqj6L3^}rFT97c*${Jd#b9oBSgImCFm<@+>%8>3}FGpB|%I7!3!3_W^YH4V?#fx|tV z>hOm_R%2}%XL$(ZU3lMyMDy>1D1~KB4pzo#aca)N>noj~z2WMw8QR13ABAJXbH!fk zn^j;OP+8>#01cF(m@rM^39SbFS-6T!PZh{pQ4TI4dI zHqNZ@56&ae0I^dZ4puwRB7b+QLX?5)zyuAWh4Yreq^4QP>P4%QG87{YEGB)DpN{}qI zi!&=#2YAr_1(un{nHHQHPh=s)7!Olc}YMt~Noh22DK{-EwI*+^__EF9ygW^X-uZF6nB_rx=2!*7?RbbKQh8?X%^D<=Jq)< zeo2Q|TwY^wWi)ZPXd>xhf-IT|_BBn{w8#@qe{jjF}Z#SY0GKS+g6{XEs%}MY}62Wrk&kI4ngk31Mu>g8Rz!aiu z()Aa_eaNe37?N5QKX#g zJ}{z$Q?c3#=LPq><0a~*aUy09r=yhOY#NnuZ=ocee3}uprV*`U(OzDe?2T^II!+IV zQ5j{^Njpt5$wG`J!<_WXm6a9jwH|{o746RPWSVcCKKt71Kixk(=I!5G8fTfbE@}0p z$qKJqJ{=2$a=W*X<=I4Ruo$W;&o+kvFsoiNh5NCtKm>coDWFiJxpVIZx7mRC>TRuq z`;&Lxd8Z|GXk5@E3Nqf&{D9rMB>YCBg?5KbVxnr=bo7Ria-*m#AkQ>H8vA&hk&RbM z{_5GYE4VVfZb@45!QLKYOO7Y>uYYv(?)BT}&u?dw$*|wg*Va%c&&BAZ(nuOmTIM<{ z5-w=aT}Cd|$%O3MGS8woiwbW391n$l#$_>z1>QD^v+?BM{$8uMl^Cllq@2{i&9G(f z3t!14u|kVvv88{)R+s7P~gn2M4>; zvBY^qndk|0Wi0a1hbf{)B-wfT!F;BI9C4Ddt?SVkuZYi{9NM~YE=Y?ej=RTVWP+-& zX<(+(^e42PaWCtXiM$xBiB0!OBw+mVUi+5MG5gqfCA`)}158ueMsyc^9B6EQ@Q-M0 z+mSdmlnuFTJQyAqWu_wwgxT%3#mKR0HwS@Z=9XX)TI%lUf1+?_NC>Kw&cHf~U@Qaj zKpcyh`St>98fcMyaBv_7YUY#SaZ_~QY_&L?vd~@av=_+$Mym68G#!ufD{o)lTt7#A zn|5xu)9ZEF0Wle~Q92qQ5r-$~!XS$!-Jdxco%zo7cj@!B)%An@Ba$QScDJ3h`Jt1j zGJV|~YiTHG$ws1;N)|4Ol8G7eUdS^^42)V#cv-L8wHqcNLg`zsL(b!@QlZHbG!Q#2 z%P$YsG+fyS)c_-EW8aHz8R<%QvIek4!neMOII6{Cl^|Bo9#;Xw6v=J@exy;bl^Sym zum>2x;c5P4zjGV*B>L_ZuB(l|a%f1P)K6=R4J;qRK?b82*gfH3DvW43M?=d&MY^)8 zJMFc^kJHn0{b5Tlm+?uc_<8CLg;A&$hEwM~cj3H+PW&>6v1{jZQO-%%xPGV`K<@jC zgivithw=7m0EKI!i@Ehz6WvF9H9I(JJO{T`9=m?dqF3&iaJ1pc-dGLoMt_lp5pG<1 zyenAH4FxG=M~$I|3)*;J1|Q;QjSL0r0BW^WwYjX+Q(`c>z)uw%QV#7r_2lJA0_f@r zX|&RDgt#8ewsyB=D&K=OWcc3NhWI%8S574PWGcnn1sJECDD{nYu~kK~!Wz8mrI64w zFR(4Iw~8rGZkA))^ZOE5IHq#X2=cSBMh+@}u)zFaUf8oPrDwH-N=&L+r?O_YePeBE z+)DYbtwJvLE}|~S0B@+`KibyNVxz*HFHss%dh7z{woI<{o!Ly}6EckjHxC%WqofV< z2+><|=AjVK!#SioGE{65A=Iy2wHs*NIj4m|l$EC{?irAcj|%$H&SlWXDm@`IxR`Q4pv7Jw>7(W{HX#zgJt}ZO zCMq#yoh6L0j5msm^+{Wzl^{%4%#i>R8L0TFM zazQ!9GNn?N=;*U(Y&2!til}g>_<3;enESo*$}41le(rOh+uhwo`4ILO5iM}7>0ZD> z^U^wG!ll6Y(X)_N{q)mM$E_5okMt9=Gv9vuZBor?3(%kRy0f#>?~|yS3i4I~?Vm1t z?b@|hUw!q;TW|3ODYBiN-G#;W>S~WjRPN55mIvbjXMFX#o|E9&b1{9#lQGAjILB&S z+VZVxS?OFx0a#k1aSjuPFEXv2_4Re6EfnKP>w`0*0)~09G!bbo%sZ&WMr2{kRtDvGR;7q(v*04#3E! z1BaO<0H>;Gh8ct}!VLVoyQ&p~qCwqSmZi-#6>~2CL=Zpb72b3;^fw1j@Af0Ce z7_;m`*?L1xH}L1@b?o{FJa{8WUb-aekXeON+ouX*oT?s(4woieHQBsfuldsn0_|=C zl36V|x%88q#ubOB+d>1E;BnI&^&_2mz$hG2C?y-`d)}+r?5I)>NR~xG_W>M!HX5WA zs?c8BF#&8|Suec_C-wmnVfMh3HWaY33A=3?!<*H;&Z?mXaPEOw$K@ z`{Us#YRAO<$*L=|oI4Qm?}eEPe7Z7Ok!NL#rfw2Pg#@5mDo>HbLZ8IC%di9{OGVoz zew!wwj<>}?N{ow(N>DB;MZJTvY14*n7xlO#%Q})o9dz2{a|$Ck&uN@+GQCF7j4#)c zm=6@+(xUnCzbJva05n8Qx(E*yB#<~Gg8r{?=?_9OQbBCbl8P#g?;xIKOUQNHOrs4c z%wq!ukqMdwmR17fi>6S8R+&))F+vvOj)>RPLRB|*BdSxPrtwo$Azr}fMcT%J6Y=2L zWtXRtEGdas&vt1+vJ>(GxCQHY6t_C0>J-xJm7a5&acfGZLJN^^{A@5Ea&JPRd^a1J$O9RFd@cT}0{4g%UpF06C-MP)+sFRoM~c_7qI=z6Hn zIo{v9w{w%rM30Y;jt__n_qrXD9B0mMbDW_iZl+>NMq%3Sk_md_+I67$Nd_#psUY)1 zOG7pe!IjLxk%K3(R&~hD9uH}@=)h<_T6oCW z=ki&*Rne(Q0SMiu(ED<9;Xe#Q%6rebE%>2}T#^hso10HP`{dKyQ9xQ}O-5rH%Ubw`HsnV6R+3`uF7SkH-+`aYu^UtRXXNK9Nb=)Eq_R7`k zy``0>pL?E-mV+@_-8$91)#dxwuaENS+Uok0JCjS-P$e;_0-bxfYNMEpt1XC#2igVM zCP=~|QHQT=$OGrn3JRuLY=LQwA-k0B^8d2;X1$gj*O_2M?BNV|9&;iylcXq$q(n^= zRTAN$pn}V8SG(Z{8~tFQ9{O3Yg>Il88ubg>{ouz!cR#d&1{&pt(Ph_zEy-@n&|pa} zijzz-Gnv!P>CX2Idx~CbeG#$aoO5puq$ErB4NzA%&)sM5*fFeF!?(Ugi*0Iyhu>iU z2lFo;dFu`f{+y0CI^yVeuAiJ{E0-=k|J-v{@SJz=-{%qA+oSbK3l-PXKi_%h%Hm=N zXlkxiIAAbmzpu#TJF~g5v9Sg~J{i(yHrI2LEago9l1tWQA}KAY&>h&L0jd9W$&l2v zw7OD5E?<|HUCzO77FV~jg-){4TVB1ivAMUuuaaJTn5_T+5CBO;K~%lsaJ+KiIl9jg zor$$gQVws@x+I0CQcXyaGEBsuq`frclKJg#r&ge^3!uT-Am@%vOwwrM&2{b0H3_0} zq6U{A7%@^&C%t}03&zSwddr%%hE>G_l@nCtDD+xFFX1t&chT9Ve1jR7r_ta?U;%Y%BQGCsm=F z_qe>ZEHxuoGjW@>l^ReRwsC@`5$<2$#e_N1w56U*nq-~4+wVwbP{%|mbMp7b**J(& zSgxPjc=F4}0kyCVBiDnEFhy$|sI)rElbu^Tf$=_2qrpu{tCz-^-taRWwqUh_*~UW=QpzPIQ*xmfdQ=Zr~{k^GjfefzR>W*$Yb2D}dWe zh1CV5GHEKQaLkcc6l2bo@AVew*XN#n@xyCdTlenLO6cS{9We|-DM;utabDi(oxga2 z2IZ(2>57wC_7C=-ec?Hh|GcA1=A|P8SWuKwUfwcuwc}NBoADzi2&VZai28aQ zr+gl#@PKVOfzsCa_;aiU1v5z$q=M- z+(^}l{?b-0(mD-ym|X2~o4^IeqTc#QvTya&qcJ`%4<)`oxOMcjXX^1)%Bcr^oa^Po zb`rbYez-DETTk)Ki~Go@u|0?6pHAh79yf6Z?Ke(5P?MdSQdcx)JZbMBHDIGjKlas( zYNa|PX~xxjS}I~Jr9^{(W+IF{d&Ak)uKjihy;8?zdaGaZFMC`P4j+qvE&@>Ti@l?mA+LH>MliJjI;HAlg7b?!Y zM=~L@-~C~qBEq12z)eR1%#-@5U67pdoG-la0;}MidD=lH5#H>)Qkma)gZ}y6 zd+!M&SBk_o8j1@SE|BU2mR$)BFlRDYOrhpN?E|1O$Qk}5<7b(O5GYKv@x%$?L;jM) zrb&o#^620wfVh?x7>*t=e%3>3OW*9I|0UiXlZTV@VVfB^XzWmrewkn>n6lp*>k_|> z5O#$}AQb;^{`GHv@rz$1^M`{@1=$|MOduos!yygbVZnKWqms)Pt!$p-G5{k-uE;@^ zMEu7FrCd1DQVBO~C&}2?a^YUpRc|4nwAI{ znY-7nU88qjU0tO+@9gY+c=alm-_(li(>!OcU9y>JY{|ysdP}?8;JFALOZ=o)LXXR~ zO2HWpeQ%AR@yp7l>&?wAE-ub*Zc=|f*xtQ!=gyJsFh{`IbsFuXf}!S+KZt07vKs(k z#EOHY)jke9i*^ga(%Dg+TB{)fjJr`!HrJP_x4o1ncOhljMZfafm1D&B=pDzS5(@)G zm1zk{fSqj>pbyv$;UAs)!g9)+!9n&0!KI>&9M36UB#90tIA0VyZH4?#Fg1y1TxTr( z(dbwaJ+-w%2f)7JdKeuRVZUQ1A{y^l433Mae1vA5qe4rqUlziZFByno!GO!lmLXk; zKG7kxG^ttcb7i~n(cZ2w8t#w)EE>+@mXh=N%KDnnox69T>+^00>kY}JK``bLwJVD{ zO5{Uvq7D?2S_+Mj^!UOTzCi2w8-MjJx(RI`+!ot`ey2|uS>0GtaxOpr9DPV)=lSQK zSK==w<&h0<6j{_je!4)y>`b}go{W5I?~V*=VYuM&XF)%-62x&+Hmzc{J&cqb<)!`X z9UgM$xc*2u)8nHjG6SrNUU^Cqs)xSPFCX`zXDWjpMWuAKhwdF?;=up!H^$~wh zEDkXE58$zbn1IC#fx;gsVYc+1x#>&~AJjl@unO1MKyAQb>(;9WA>O#0t0umumZ6rL z2$Iu)-c!)UTt_!eQubNa96Zg$i>wknMNsBODxEf!H^o_5NvDLYZ(%jlQ|Znw1g@;> zxx~=Q@OIY0IE8~+v7&5ETI=j!SndysPA?HP+Hi}!G`vU|fjpu$RTQjVAeVLWi>~Li zKO7&a&$7lZd}YGGyxu~8ad|n<7g)*Y_DtS2!hf!CUP~Z2?VuPBZ*3Dsy(G1Z3(Mp2u(B1hn;38??1icD)qyFCQ723-j8r71 zEp^ioL71Qbr8+a5sF>3mDA^q~y9=7ZXuQ3T6vX-ye>0rngV>!|}H{wF6ZGvl`_>=FG;5UR5^^9XZ_YSMrYi44p%&$3QV|EXS= zcUxg=i3@8(f+At!h1%u`yDbvUG2!mq0%^31c_+|OAOeieaEYU;J)eRkUhJM&nj;n=?hA%mZ3>e=`kE)7KwBXu0J$@qL(4|CFJ&C{U0`|i6( z`?L$xV&A}DM2h>_vuB&Cu13RD*`7AdU|0_as@q9q8FppcF~1gBFT-I%7Fx+0b;y~G z9ksMzdcCSYM^<3cn`@Sqs+GkZMjs@}%Ep}!Z_{+_7K7nYt&X^cgs!u}un?OhV_FEB z-SM!lxCC&XC!qpua1F;Y%^6Nn@e-?@n3IJr)*T>2ILjD)LvLA%q$w530%(NUNm6K9 zdeykdlN?rPzqbfHHvCzbul@afsiVdp(+Z+>XCw_6z9bMAM}$VLeQqMA7Q96;fQ_#S zXT=4B1aBqY`OKseuTw~suZ56LXZhf0Ah`f+K+?qwSeTIhjW^*G%2qW^*traX(=Gd` z+@1fSB^S3t!X>AD!0Gs1%ZIO$(0MHbs)QQFB6n1Iuf*dkYI3F99U|VxVgnb5{D-6i z8V&dqU=OpMFT|yCf;Yk)UP&ymMgeeIs|^$WOFjr^r#pZsK$!jI)j&pw&+#}g*au4( za!brh@!wkbZeg7!MN#eUY^MpyoBsORCLIHC6Vn&>NqZ=us#wjH5h_}AG+9WmAOjd> z?W6@e{-e>uQj2p#T;^ve+J@zOf5(@O!DrJk|C| zfa5t`uB9&0lUMmZDuj|k*Nyu`DW477Vg}pb9jn(QZ7H+tH=99;5)7J7w z|N6(*+1$I&bfb;*Jls(9eRAoC@^dzg?n(PuJ^GSIwUd_LM=<0*vhDYC@L!xXJC9>j zKm5HOhGB@?$uD`*{o@pKzh`ki)-LRPK+5k>udJ-V{ajYU2JG2o`Q@Fl9hhRCdJKT%yyuN7UbZ6-g8gWJt zbvmSn2el?V+uAnm8LGmuV1S43HwOiXl13(yNt^=8GkE|0{Y#fFHLfxw#uFu=VBW_H zYZT^1u2K4NJ>nnd>)|F(dLJt_yGgeoJ(%8_v|i&`cHsMm#()S+_*SgdL4zUl@6t2R zuCK2{pIBX6lab-MP7_ww60w@#&8Wn1RW<1H8n9*3eSj)LF@Q?ca56KHiiQ{ns~Wb& z}yYt{MymyW4kZDoO32y_|Qu0&=Sm|3sc%;%fyfi7;3xazleq`Ff0`3~>x$ zC@@#+Dog^P7>b@l>1l)|dnCs5=RWtj3l}cjy!qkk>gu>+7Sm4G@k0tU#E`wAQDdVR zOIRxpYaWW1bBMSAmm6?VlH4zl8o{!%Q8XZcMX2)tuqbfRi)t+x?0Kj)=)a5IiQY_I zf>u4Nub<>qQ77-a*gT7iiv&PH=y|xTk143&4}IXs`e=Eo0W!%@P!tbZT3Vvl7tU?&RVt1} z$Rz}YP!Sia3raQy99SNVVbH4Myx%ZE)(6|e_yFx0@|kCcaZ0_bBWm==+2D|Gr6)3= zf714*?SMDJu+R-jBY)+USFkWh?)~ToKcF!`*f|;&?9^ReF7MsDM+<3VZ3R0Nx$azm z3al25R6(ye?5@Tw2oOfg;_7-=*v4cfJfDoXYudS`U_#(58z4g{xH*VaZO$3k#3}6*GI^$Jw z?3C$1Vc>FYxSuFVO%ov;-WE|`i;4`^NV%q-T(3xUhcz~Z#h6+%VNK$A#n`4&^8%4x zC8@t%k(`|Pnu;~T1)@-DQj9~#g?_x(^)VYdR!3be;GF;f5CBO;K~x1ol*bfsy*jC! zNfLnbN%omjioqIEi&6{1u9B1l?8Kd&9riwq*yV>qJe9)jD$VFt_qMs9SEg73!;L#; z{!zzt4JtT=968y`NzxX)F;U#Umh}MXG#YYV{U7|nAJAFzgCBmMI!QZ&X5{{ZA)Tc! ze&%`FTnB?8t===|&!ZIZ<;#~FUqYE>K9oi6;62eQJwEWG$Swf5djIv3J`3QQD-fbo{(H1qGitJ}KGebb=?6 zFM03o1C!}<=PnEmIiE_rYFbhiEC6ze<7BQfPW5CaT4fp2!s*(YGjjMi($$z$ZOxuk zx}qXQ)ES%-VY3-~UfIh<|6|0n21Ao!-v2}k6S81JDp7rG8-R83G{AuyTlv(y089t} zo(Te{t^g>V7%9oA0An-ibAF6bcWlz`#_@DaUDF^^hx8<)(_U9AlvT(J4zgusRn%Ni zK37f%O8sBU%ro+K2r#=hO`@rl@!`B;<&cMUi0<=`MABjrzjZ-yet;3O3i@Qa6*$qR{u<; zeAolVv$=#%=oBaA=`a4`FQCuSkN_}A{h^<987U1ghB@!ZI6pLVKPRS1*u~zTpL_MS zFE6idlDfuNu}-IClg(6eEh(Ae#}NfW@_wZXClkuoT(&|<;5X~^(xj`Uqy)PiBrsXH zbYZ7_05i;$<+^!C-atG>8j052x1+()&0E)YAKaIA7aYQi^L;HLFWPAv>nqzk_xp3* z#L+4X>auQjcX#P2q(xnR?pZ5TH&Px0m4P_!!ifpYfvcgxh-n0@V=^2bV%?LTMq{yN+qdphKeNPHcPtxnx{^c+bM|IwhYQ;p9@4tzBEw`X19dMeO7M^{w3@gOSIZLT z<}}fOv{;|>kz{P%&*?eIndB9irx+`?;&_6*Jyr`N#hAh8ycZ;(FRRhEaVmB4sWxQ; z$5+MK3W!%AZ%_yVC!u;;U@?|CfR(3sVVhIg?Y-R}fAG$0zy8&dOxg~Y-%%Xx@q#Q% zvczOIPgMiw2q~ahw*&nZs%|Cm+ot=+y6JdS)}C9t@w|79vY^u_s}n9|mgXc9^uk=ew34oFlF3x0Y+Mag zI-nUIv-we%wjNg9jWeG)d%pX@```cm_dmRHl}zGtBuNmO{h^#5$>Za4GyqeF{T!LN zJZ?y{R}LsEUfqa$cCt;|X+Xom$x{lvHZw@5=GmcLBM5pnq_dPC0ViFWT>Q^jfGIv2YMI-r*Z~O%atJqAfIm|8wD!WQ0P(X@-E0Y6ieJe(C<0;c?sdYr( zTIlwf*o?$-mK_d`!hXca)3WOI<{Uzblm?j)xf@(+M!ez7iAB$1Nv^W9XU_r%@VYcQ zNv~eL`qrE8&~1O^U;g^@&p(d>6Is9e^2;xeigCBsAA78|3a)vVm)?>ytB8)&wzV7Z ziHpYaQWv#~r6B7bfTwdx@bQYoL}qNPn;nw_EZrzW-;Vj#F>PAk^U>oZx=)l>?63o| zS3MQ99y(u7e{15NMxAgf{erb)vU#OFZiMf+7LDOV>^E-p%+nvgJ=wRO(CF1Ozx>qO zFWSQR`Hc^1p}41>@K|R6BU0)vngHghqOjH2q84JPY7l<1RQ1A3Ovi~MP0mt@QyB(9 zRhB_hd54W&Q?Z)GRQ??65bvEyju%yU90DV97~r^_)uK!!C}WtSkJ&c3Mzs*=HV*7H zFsRp0K)>{Hn(>96tw4jg`i`&o*D+EoDw6e1LDWwBuP4jCP0es{w>u@nA8as_!tc1) zMFzx(O(#Pu;KX7S79+D0U!cg&_H6(cLFm59QyaTxjpyTiNQ5ebvLJ1h^Z>dNu`)8i*#6NR13{DknilEX z5;KuGRgUY$NU1H{ki9q>#TW#aCLw5L>wqdmfPz!sLTw)B#%g)?Y1@)I#R;N^hX7D` z6rx2GlvGLJ&>COj54H-a`$#z>4M})h-3{de7sFAac8J=`fAW>9ks;>zqL4~GC+UtH zJ?Xkgg7GkB<5OovZ!VDzinWBC;V^@EsE$Hd>g1)u1A?`bv{Y50yjFO+<6ZPiMUpx_b(<66^h&AOHGgbprj)$+N^2)=;K}AAatX$h^vn6a6}fGT;c#@ck60p0W+BH? zQnZHjc={Ye5N=flY8zqmCKoG{v}alyI1z#v zDT|hm+D7!$^$c!V`#5Agr1b>B=J5mAuDTgpH|+F>7{Ea-nhN5hs{yx(@E4xNV{20o zq;G6&(A(4RH*VaZD>Ly{0+c&cY?>wo8x^Kvny3tDQLbi?HZnn>GmVro3UVOJrF^qM}70VYF>2a9WG!rC9-Dddv`#7pn zBW$a)QE@An7ic^53yleNJKzp##`TJ=#nd}Jx@FR_y}_rhq00&?H#DT+vrf0a=h4 zIG>d(f&$2HJVX-#Nh8dCJiImU0;RG28{D6!34v?+g$?^e@KaR*o`w4l?k%mXq1%sn z?(4~LXwYp!gA8of*aVH%FK#&G>~jj%9jgw-DfdY!bf zsu)+u_Hhvf2uBw|lxmQCE?OjC*qY9Pj^VQ26QwkWbVQV)Ns($0c@x@MrfWemvSWdkLbIyY z((A^Zd3+Nx(r8FQSZovKf~qClCr|Yta2749yPCK~}LCq~LUA}zz(#2<KzBcBr2)ZxG6{D!C*vcSe|hHe^FE%ZE@&aF1U1Q07VG!IP&oB@tJY5{5RA#UA|JH(4g@neo^&Ot z6L1S@2@=BWr*+PN@)}Mwt<ekk6x^m;p=E~YCJ(1S@{%%Ras$jDI7EJcF8oQpD;F7R+e^l zc5YmKpDtMKGm#aeYnpmc9C6UED(Q@r;Am4MIfH&XbF@qAUPh+Op|*LV%S6nBl&j7c zMryy8&3q?Ug)IyFiOZk-?|%Dt$zuHe_rITH9opTi>rBa;!ujPAd|Xut*l+E7$st?v zRvp5Hm-pD|OiP8y%EUlQ49D^Okc$6QBmS1aZ)JTE5hG88NHhYa&T82i+h06j!jaD@n7_)aU7(RILU}0g&%~3i*cKY~hQuu@!z)ZT9RM5zTXi~}Y z%t3*6@#01L1(m?El+oHG%BOCHpJ_MMl}3#K368Q(HeUbi{^?4HwBo%I9W%;Sg zm*_=S*VZeMu}1isu`(Pl$zzY-gp0)2M2SYET^Cea_C6y@IPhm#S- zWcukLqC3^+iBQMvJ)=*axNrY7S~l}Z9AW-g1vO9GKjD@JXMCD!Scg$LcRrvQSC}Zo zorHO^J%D2c1y&L=05wX&=sJL-yz}0XG}2eB^6$Dn3>Pt{(Fo9^;LqyAc zYqCpIODHUC?W5@UWJ?W(IX~eSMQY?{@m=twd{u zdtCNfRq}c`8V)3&hbVmm#3r?i7cXyYY;=45zDh<$9gYsku0!}2V@UHgINZl#gI%E_ zV*?CKv6jiv>8g&$VRquCt`COX)G$Veg}V}fWHm`~td5t!({0LN4ud?q#-@BIMhKjE z#Cn~8D@MZP)%V_|!CvYx>~>I$MQ(_rqyZ$yRqG)Gpg%Xy&abW%r$t#fku!~lJP6U9 zo0r|)UHa?u&p(f!G|^YCTp=lh0GhlDgFci`h*dLq87yEJqS`+q&0F><{tn==LH4n~zfXS|kJatUghC@7# zHU$aaS6+FgC_%*_1raP)jo#a3?(PS>dmn!I;TOK}Dt&V1Y+Jj_`UvDBTX;dHSn);3 z>FFJh9iU%GPSYn(Km9bsGOtP9mgI0gD6m6E^%}g(0J%+k#N@)Fa_-zYnj_3ICXNaA zd;q;gUZM=g5) zM92N?#bNr)licUDown2V&%CudD~nn_!hKxNI+i{9FHO{)+god^%XEINtt}<~EEn;| zqKAzl10W$M9tnRITNVx1d`l&M%M=SuL3)zOIwQ-9xMqB)?Kicty3Yn~Iw!TUY8^wNI-Cg;v+(9yy!Cu%@wNOy#jvRe-QEhZb zyz;ep26B`mRZ@Fdz9lCIJ4+jvE#uK_7HrO<9LV%puzw}mDEE${?h9p-n?IU&g`<>f zEOUnwm36avzm(IB$E_KUgzAH%2+WG9IcHUQNH#kuI4CGFV)-1kk*xp#>PEAYq71@X z$`5qrDknNVttrLVoobQ#^_Y!Ug^!TLO6`=@gg^Nh)dXmq4(!d1v$zt#hhkiDW#FK% zH>fbI`~5jmH}7oSJA3}Z(b4ec?Ry*_Fqze(g~hd_LAkxR|D!j4{FSf%YLZk?AUIvv zWezi*SBz4_*@M>PS$F?%mo$TJzjJtW7;J1Scys7p=&EQfRZ%1(A(-JJ*>zz>e_ELD zck=Z9or9zOy}BCi@7?e9Tu_UNWMw=^f7;sG`r6mN#CYnuo^ll*-kX8DE1s9|i`0H=q!$4qaC9(>09losh)&zdscF)LaR4N4{4+rcy<|<>CKa%! z-QM1ot*2dRNVU5DY@0IkA}bdar>pQ+XW)5WWO+~a93@f#64J90xydSc!}+~3`#gXn zxDwLzjW^y{U1jdpO3dcHg9BDB(@f?_;HiR`uY?w#GZ|@ZSax610+X1MmGYg%y?ghR zTI(+@(R1(K+rpx{c<~}r2i0u&rJYoA&Pz^qP3b}VH0+#L*;p>uOdXX1<5p&aWlqXj zSc%wBo%%S7t7BY(mtMxhbYI593j96 z!SfWBTnItpCqzLP6_0&IB{l{u*A_l^=Is6Z_s55W)ape(T5O+|cUk9SM$R7yj6YwY zkx%orWwN5i@{YA+A1ENnory_vF(QMF?lCGW$0uji;>s!w!tJ|v*k@FgJ)(>W>zvqRSj=il#D85>WJVuq>>=29HTGWHpm@C034>2aa0-7 zUyFF48{Uw}09XNC45&7+%CZ!|m_;O${qL8@q<+dpaX%CW#U zji4m_qouo6a9(_Z((xp;Pi2A#+tC$qqZl+?LNiLyJvPYid;X7WtnDql>Sj4w-KyMq*R(9SF}wtppSR zurX$;l8soh)M`LG!ppKYifrE`GbFiy;OnHx>eAxb&2?Ls8*6Kp7b-KA+9tv>=ysL5 zW_0+ZQPZv~VTZ9mpD|4gBPLipdNj?$Tcq9j!{?z_ezbPdciSkXm6O5~l;RWl)twi! zy_&t}FIw#PaaR6Gm4QG0Q%y_Js}PPoD6(Ss zw%ZSlSoENE-HxRH`2+{AQ4JrGcx@Y$AqO4sc3)}#adv)NXAhmA;`plWJPeQ z5?ij7GpH2)uZ;+`AVa5{Dg>^TnvB`bMgyYK2q(5ln9a0#JXuZ&=5BOJ(q_~&zWQSL zJ@hB`!MApTvoV~az)F?B^@R30iSiA>aOJg@V-y``fz@9z3u*U0hsDvpy-HtN-QCH#Rov#=QRe>nrOUG@b{C0~y|K z8`&^SKV!6`c=_fxze!5S3opDtrjAdnb=?Dm6aFYTOVO&`X&A+=R0(>F53(pAKTg-;IaPFEb|}+Uv1BwOeVjdfVc_NawT2#?TT|Gm7-aY39E|>v%&Cj{>W365=3LkP~|FX$kedH6pj396`?JZ zr=keGntkZ(-itSyanyAD3xw6U8scstU6zE6j887oIayelg!18J}%XHVY8Z#Z8B1XO?*9pGdo{>m(8 ziESlDjSGMvfE!4@S|k3iYvB&mty@7kpc6Cm*M|+A8bW|?=evC@BlOnY2Ehc)_xiLeA-UiFLiSf z;D)`TbT}y3R&7MlDY8ro&G9C!MrK3OIi`($<+A{B^iI9QPwjftXhXgpO+ z!WO*?YBcaii2Vt}Ku&8UYe8H#N{4x3P2H5j$?OkcH;p>fh(PbO71aOE0|?PH0$VutlLO%*`#(@9%x^KIvGyJBMUy?(FZe%A3tCuduh9VWM5; z)V;TJcrL>+0UN4u*t+ZgRvuds!Lk-ojlh`HXPUU3rk=7SHCeD z5ANQ*iyB23UV$(e;bEl(17&wis!Xq&nOYql?9;`)PF6SN4}S37YuB!ghg_tD40#Fe z3ZrbrO5w%Jmwx=?A9uU`7himFVPOIHX9W=sBY9EAQDYq>S}KJir9$B$>y@c z#;lu=#Y9Vq?RhrMOvZ%pNe+EoBD%cZgiKl}YE)auRA>lnP@Aj=SfaVo;m3Qtuk#=HQ%4p@rL^rXA zUh@61OWc2rEu3lO9%>{*x|S;G602sMCn?9Hqk}`vK20-5)%STFy671XsY46b7Kta= zu%;;MyW0<>#xlS7cvR9?7nhf4=vF&D(x(6QZ~fN({yxn${a%dAPOn=vCC7LayBf2E z;p+`2LonRnXfz}Rn$~=5x3~%dlRgU=C+hgkI5Eg4Tr+XOL)t^GnKG#GOEQ^(Y@-@f zI{K4!_;=4s*EGFOx3{{=jsP(yx`mWGDus&1CkF8lEM%`9P2^Dn;o`sYTYx8HvI+u#27*49>KoB3Y<>8GDA z8z%P-0AM*l!RjP5lg!i3yP(tQ_2=hkLIq&YS)IWEhEoEBa7OS29Ji~D#Ppb)U5?j6 z`9m;q4jm*Y$@z%0Eb>&sj0ac-JFC+X=yjf%EX{k}=RWy7{S^RQ?-7%nCSUtKWFuHu zP;zeB))>=zvUC=+X&9klP>6F<|Al@`Aii0LM;Nr2mu3cw0DEF}aB!iO(H&=g$# zn#1E{KD$B&jRIs{$#-DNIxGM*ixxTq^U~D-fnOqWE+?@yzeXJZ01yC4L_t&u9d?;c z6LHTm8YRh6TKsvZ-(8q%5>pF(hSARFj#K{QZ~_0aH(wn9V}O*06Zoi4+i5#(Kc(h! zJZhHs6Bdfo0Q^7cgd&-1rAn#E_Jh~=zG7sq*yj{v)8!2pg-&6u_UqXB)3Pa8g5n`1qi&<17?Sbba&HN3C(F=Tnu zI3E}$tJ5{;+@&eR(T-A+GItG(rKxC4{1gQ4D(4=4GS6;2_-ZEK?`PVqk6MS+so2B{ z|AaY8zd#GQckkZn>M9w)WC>Ir$WRKmxxyHhLRyouO4RSqEiW(A#T*9N-xuFXlC)JW z#Y11$q?wJ1@y^c9!Qme0QaPm4*x=5np2k zYimcNBa%PZ`-g`+NV9|_q1_Eboi64NGZt3B9^(u`@^&g9^RncOSvtV!J`iYoyLTj9 zjF27Vk_iLor$g{Qw$0*J!bptq!5A{ro}}Q)u1>J7mX?;7n84SF4l@F@1%O3icKnD< zkCF-bAnnY8y5Cw~!q;T%Ym-9D9VIo=k(Av?jVKtvVWJzKHydd4wQ!_|E~U9tZqFE- z)1PA%Xj~2G2N}RT0a+gu9&IICiQIbA+MTwK)3kROfr8!$8wG|m&pWiP;D{7=MuIE` zZ8<({QhuVbRgC|_jPqG0BZ*9Y`nkKi3+xYsQe76>V@#AUJt!cOR*^XAAhwf4Fk$0| z)u_aU&m)5{yLcITi}RbCnPpOrRlQ0CbXD@v!i1z82V*Zayo_G+@+wOM=cUWy(;gA4I1RFl z)J+?-YUH#ep&Y6|CIb+!9WzHJ85^1H?>eG}3V9rUD3Ap!XFrAqAyVs9dRQz>|7p^%^$zLe|SX3YG-b-<`vfz zG&Q1NHCzoN;h<@f32#dJYTT zxO`0s<49g^;y`i8*W<-mH8e-TNmZ_=PHL$WckL?(ACj5#RyK^_tHc0SD`a~Pl6S0S)l_u|Ba6@ob~x6XbJEF>GM#lJ<#T-$%c7r>Z}?c4#`qd2 z!4h;*Dw;SNg!zT8lpMycmi@`eoD9G=o>DrZ6mM%LXi4L#=qUfnLIW-Ht6vbm_LvNyL-NR0hpZ*-uU z=gA%(HRFSS`SiKr!7f*`>o1AFCIOU`4?Sm281X`iBsWaIpV9`e8;QT>9Y#Z^hX;dR zckXka``ok7K70S}o$q|-JBNGw^m%t~{vZC~%B!!w$}X*}BOX$9bTlNR;?}KOB%Ns1 z=%>Uao$pe4POq08GDwTVw8bu9rpk?B+DZ_wU`JyOAcKgveI_AbbZD zDMVV3PdP>+Xi5v2Hss#!5&g$8Wd5g_pIh#A>nvp}z0>C;i`A8ldv|vv+d>8EU=2?P zW5kNGYS=lW;u+D-S>vb6FEHf}Iam7>o7jr4O;T7hP6tQg{4XN%hv9TWnGqIs}c-T&KNmpGJH4Kx8Iju!8P_qsib* zcf}VU=Fio>^by^MHYQvcbh1Fop@tAA{O|4c`kmXiZ#%c9D-m4MOpOLZ=9J=4L9JL^ zTY*T|2(VLc86VW^-Mo2|{`7?}d=B!KjQK_qv&DPX)=biFDR%qwaVqjZc&a9R}jchol)oKsP>ZH4x;eR?BH4 z7_o>7uEbUua%N{GFi2zzOBgm2>Jf$bgCG@!QLu3SemTP=lSdgjz;y0|ORln|vuTwM zhAxT^naCOMWwgs?5oN2jByImgrM{L>&<*yCKnzbO&P_ z0!NQ*kJQn_W!hJKRndW`qVyipN1^fpA|;ry1q2G%9IA}y1)&xMPZ0?rmc6Q9ivN*EZoWP6N<1BvrT44i%wg*^x`Dp}@q zbL!jozV|(P9NEv}(y{>nPo1RcLpX?jE-$Z=!6TT-%KA)x%s%Py<53;q{n_Kroy z%w)o(@~aC$0PC~bU=Ui*?5ZQWW+Pd4XyKl`_EM+3y0mA%Fl<0RpJ4FBJ(?_Bg#8=_fz%jG8w>=oNtUqC8HWB5IouPFJ*cmIR86#yy zaBmTrJoRJEd5n2pOCtIh1~7B=%k^|6BTg4s(abZB7mX{fN{u~x{l;xZD6qEA2G6~F z_rCFsZ-nrgZN`X`%fOTv6L5gbThw9g1-nsxZ>`WU`)q`G2yr+mT-A5gOpTblXh(?7Eq)TCgvQG!O8j-ZauiZ6ZK4a4tjMac3d91BaaE?92NFU*tZSYKVC2fg#=TR-^057su%&>fgq z-k8nJO_D0~^#>0g{N-Q%<@M{=-+%voK-tM0!U2rchy;^wed}Aar{?=}=gysb;f3eP z4BlK@KY#vwBe8wj_zVfDj&LIIdo@hxg#ucnjq^6d-tlK83rz8@)xJg%b|1|P zU?ZecR*LJY0MYVk2(u2X$C3Q8Aw>5;l5-+uiG>tUq=Zg_v}6~`1^8}==uVA)y#2!~2NVy> zZNZVDw$kd_2Cda|7oVb^m5!e>k&F<}e)#b5hw&G`owT<9DZJZhJ8i#gEmiDl<%C^b zt3onyk{G#T-EUl;4pnW~%bStZO42Upnpnn2tmcxE5<-gxfX~B^CBAv|lMO zV<4BEj^yA{96+sGpiWsiGhQmY3Z{;G%I0-@Sc+ESA$sWS8gw(9klrw*z+WS(@p|M{e=c2 zCVIHU%^gWtlVu&Q*Fi&+sQFHRb$OYzF6cVLku6zK!x4+neruC765jxkwv|G+kJDlm z`Qx>?nxAP`uy64RBuDr$2XIW$;R#WBose32_wHR%uLqwj*>Wgx{N9TZo{$eGw& z787YuLe`e&S$E7#uSl=0f)(K(A;`C;9*svuH6D$I#b{Wv0?NtQj_VtSL@j`ds!*h} zHdUhRovqtkv}Uyb$AA3CnbBKYTd#cPrJFZz(nBRH7jKcNI-$!*!5tTcM1dBT7Z-N- z_mtQBWxa4Wke^&t1!CaN6XulER_Ux=?yePja*knI)7Bx>F7Bbm#SoczoMWup@#mic z+=z6iHWnAa;m|3;?Mwq{y^e)(bI^UsLyjF5_{F&i8ZEid?0SGL*Xd@ftE-?gVwPwI zK^SF7-yMoE!z%rh#`mPUmln_jjpY9Rkua$m;nb;x=(UolGTyWbuvq^#Eb?kWu*k@h zyr_gvS=hhX`iBRq%uIJQ9G6FXe4ko!&O5C7FZ7vl*Q7bU%dXG|>Q3ItGkajWbKNxK z;od&jU)fk04~DzDyW{cj<(EFQwLHFC!Icr*~oBFl-6hHjARy3F&YXvUIzAqn1* zX3S)To)1s?H{x97jA!uRU=Ju$3G^zzBL8jEh=a)7k}Ntnx{C6*^GrCnQI3SsUv0+<5#!{{Xbq|}DLcW+2-8pT&F8wk`Ch-DXLFsrmnH>Ef2^3M^@H13 z6PUIqVPxW#gm+*@+W7&8a$sb{Z4kL&T_H=?V}LYdwZt+F%=nFS z=hxQO7FL$!q(mo82nU3H*Y0=Se)u@z7d#^l>GrXCH2<+1`v1>4C;GIVwx35!#bK|c zj%cuuCa!1%#1m8!=`_Hi1VZeGPym1fp^53lmwp(q$bRF>!W^3f^Mz!K3_xyEd-CDLIUZao1Z9zjUhV zWa%U1$;1!D|H)B%eA-NiCx~eTq?A*8XU9BTAL4{jr25gqy*v~3+_-TA-Zz>f`UP0o2M-=# zkt<(YUU|dD`XC{)48SZ+UuS;l#d(qmv`}ePNR|hecn}(PUQ1;$;32Z5MCAEasd48B z{VXK=wBu1Eg5+}EL%}RKlQJ+z09li!ZjR(nEiv`fM1+xbYLj=1 zkI^tD{)??dihXC}amn?8U>O2gCQ^!Qc%kf)sJ@&jw8%+P(J(SDI!SFdp>>2+6!m-> z#ETt)(gTPpyJ)r}dPrrH&U19S9PaJyojG%c!7P%dG%E=w4nC2b*idvXY;0`I&oiw9 z;9a_!0L00aAQ^3`8I()fitg<9eh>naO$8vd^#C!;cD$#BS})XJ!2L750^YwZkI zW<7P7G+T;jF6Ag?&B-B-m}66SN-pn_XsHRz)oqQawKnD2eGMHRbpOF2!@8;lAtoiy zN`@oS&${K9OL~ZHELn?ILV^v9Pe}15l(SWbzu;39vG%3;}qD0#s;@D@_BwT?J5#GS3s z7w<@wqtS9Ar4rhbd9t2*{RRbWjFi?WrTB{6ayXO{SCZ#utUm+oZc{z!3GS7A7+!a9+r9*rtKZG3Si`G=7trL=aQ_+Vhm?JZ*aqLD}^K!DUt zl%ZnH6&gmrKhLqU^6vHP*H_mz-hco7#YK*@-M_#6)KgF0d$2>==lmk)`*F&$kz_xf zi-i8GrLYj`tfX8fQaaLU_7Wywa_pwERoRq5iV0L*}uxie#4wf1Xq%gu@Ai63O%n@w1O)X zv!x9M${)8=IDyRu8>f;AqEa5%l{$86tFEnId0w|{V>q#*=2cIgqrBVc&2_%@t#2W7 zK3pJFy9za_0KK5;PgDXFh>`qgNQN3Vyu?&e4Z?RpBBbmKsB#j8HfzexoVoRrcj=`r zU;4zx`ts#V=eUknowGA#Zk?_imTW93nIy8R=#%F@^#Y0Lzu(X?>kg|Sufs%YR+mzLl_RxQg{&4I!&W}%#vUkBcIWzE|N7Ty zA^nH{@ITYY-@SX6)>Ws|qbUYrLh_$o*bm7kos0~wQjIvvGz~_zY~m@)2eS}NS&+u7 z7BE?>Njd37v1z5%RD0d{^c-38VwA!?;oN5}(HHR7mF$tGE^JvGeMnoqv$((y z>L~M9fAKe8`)_`ew#??{>aZwHBODnV=;qk5oK(!5kVstv8d~Z>W)k|ZlXg0JhbNjj zvAFYjlHR{__vxoD{r>M=yn6k{rAyC{z&UsB9GKOO6lDJDYhPtnvu^LLx89<8ozQmr|W=wQP~!`ku+#)MfO>iWuiSAO!&TVzYW`o+&KEiI*x=Lg$$B}L&uElG3f zYQHNuJ$Z8(K9@&g%F-vF?91t+Aua@MuiWYFlI^YXSzg@#idHq)r&u_1 z=sH{I=i-`AX%+;_#FG1pbXVNHf5$@a~)bsF%xF0!=4<#2gH1Kof%2}ee& z44_tmcc_#8Wp*FzN%*%JkC}Vl7^aiRvhKn{pL$BCFYQ?pr=S1)=kMIP!|se+FQmPq zwBnNPGFGGw(7jTUU#ToMZ`}@O^F)0Tl=3<=d%`?a-?cktc+)B;qISX^(iD*se zu!SFD4;v5nG9NE@_GfK^+7qgWxG{5?z!8?p_2&^W@OWf?8r}Q|EqVKG)OJ;87F@p%}L-t4qOO zs6}LVJAKafIb?3$UZ*eFCN8aro&`$GOj@tg^@GV=KJ-_Xw(_zeyT<+0t*R8%DU5@i zjxg9+DLmC?BNE46A9=ecK8e2`?T|RSd(53fKc}7^2Rt8Vzr~(%6ah+dCEVI{z_Z(; zDiXoIRUnBCSb&)hAK%2c&?>Cqp;NE(IBn{5jPKAoBXkqu4BB&DN}qLz#)qbSkPt5g zla=(3+qZAuym5PTbCdq`o4@&+b!{(PxbWePTi32#d+&oQ+uPfXIBOcf)UmBfjt(6j z4cUCPtgP55TxP6uRaC;j6bd{BU}xhS9g2be3Ncmc5ADQne(Re*`q7WpS65zn zTGC-C@JqkX1yR=5*U8BF^FROdU-^|^K^@l+<3$J>QC8{(8R2KnoCy@rN+NZ~0@T|< zo>{IKGz1R;e??{K@Wqh+7s3S?1WsSHmQ$cZ%oY>pbY2}>(eb2*e|nuvSeh#KaP_)# z5<=w}Nm5Bc49cgcyh6Hi=znn5JW}}x;}Db;1e$K$y0x>j6YmS$7O^9IfG>xq;7Sa& z3(L!E)yI`&(>`W}j6Ql64cgB3*0aw(`}8M1Lz8=LR}wG#GRp`p=FIX9m?bIhWcH9; z<;>6V0E5q~F-qn{Ll6mJ9A?}Zji$U9@!pBo9zAz!Ym4^Cr#|(mKl-CTT3cHq{Tqus z_*MXB;1?9>ooC3jl%TgZA>2KSk#SF%oPy|=6C<}FARKGh@$bjnFe2bl6D}C1q@uK` zoLmf@815h5xpV)$_ujjF`7%nmVqYU3ZXDtPtCYXnNS(6GHylqg0Q{89x zNkJfjW{ZAy?YYil35mG#f5zJA3Qra7EbKDm0AnRkPe>$^Oh#~6A`RS-T;1)ZoM>Qq z^WNFI6|eI~a)6bf_UI0DTM&5wn-F^F&?T``GAhj8)bWepf>t}y9=xN1IEn}kF*5io zi1f$+W~@`qa%OPI6`S{V51?Jpn_k#F!p?oKb{eI+D_YP`(Df3M1FG^{wYk3q{Wiw4rXvPo5uFwIEG%vD}DsV&%$ zF2q&dxbsiy*(NzerXYM^0MCi6%p(IBKFCaa!i@P|KNL!VY$XGjwJ5G_Nx$b{`PV*y zlLS58SVUo+%LD050a+2XqX8=cu#jq-7Aiul3L^#*&4x485MHa{yjJ2#UUfSG zN8S1zCC|sCGzK+0>U9}kr1LbRrJ{u-89*$PrX{<@dF@nUq@;jwYjsSqCUlq0yoefY z(#)vE2;doyVB061Yf}m?o@-k(1|vWHEpLs;HSz`6fyy0*C{#ZH01yC4L_t)sMgXzw z%O}0$=FOW*C*x7My1L3LV~6z>YiQ|q7Z+BSmyWV@D={7Zw&WBb?!c9=b=DLOl$*h5 zbmz_;RW}^lNrVrkp%v#!XpRTNVmPYCg~U6!Di8Al2^>twu^bqZRMCM@D;?}G47;1? zxjd~$!(N(Pe60o=;cLUhww5qb!N=!W@4KN zj>Dwjb#K>+WVmsVC7{i1#Yvqq+RRWV^*3QrgWLyqwkrgRaST@*H5)iz`(dhvIK*m**YLaN<(Ge3xg|!h` zM31ONJ*DWwVA~rUUf;T9bh^8@?efE!&7e>u7;C>Lq}--8fF8gw;32ATH!!T$fE22x zWGZa=T1CT^+LGqEC-g?$M7$@vTh&5lJIV4~mNcWo9eOUuSelf@U(GRFSI&piMH58^ z(&s<_`Tc`kdd<45I6p$XJzzsHoW`G6lEA{`kO=xcp-D)yf<>ap{|U>)t)JH5(dlSd zEH16Q`PMrNi>vD!=g7=xYE#w>y`ljO7 zGPu%!g%$=4^Wld#mY3F7mN&+u|0)SdgZ(re z6i35Pe&U6V<>hX+Pzg}hGRLoE`3v*=j8~U$MpiBNfyayaD|k+Y(VRwzGvIYvDe57= zpwMZt=8$E)nq)$RVgnE>i5k@npEr#_KDaD{MtIM~5-Q{BBve#cOj?OUNt{kp2A*qMvE&8WUL|`1}qFDic9blh$LNIU;psN4MC6a`;CX} zF-(~{t!kpi_&ZmPSl@f_fNku4pT5hM(}2M;Kv*LBIEKyEhiUkN-wL|MsZv zArAa=>B?z4ZU5|BdQ6zn>Dl2|_eB(M6oeT6HSclkS4*rI zZup=F)7|K32Y)G@CCkgJ3kwU~Zl8X?bmX5caH*nZ`jF@Z^|jB{)7g z;@<(gisL!%bNLyYqp_0hb-UIJ9uo!Qv}#=aY>s)v$h!T_F!yen_;VKGV?MyLXTF z8I3SPoy}x9P3clgGaj2&*l}*wB3mxR&5(jC<19+1;4h>wdp0^8UB7;P_i*?5=bu0S z%u9^kuQaX3qmnx|swD1bnGbC10d=pYKb<*qW-vU&2*km8r94}K?{MNt!Yj*xsaZGx zSFVaSJM2AL*nj=ke@*}V>}NjIOz5 zo^R$!s%t%I22ZVrsr^3nPwm;)VtXJqdLb3P`1QzY=g>4kG9%R=>9rS^FOr%1=J(#c zcIjGwex7zcZGX;bm+1?O8C7|;#DuLdFNDq@{%?GFHpJfPTeLCgZglqDzI_{l`ta}& zBeA!)_vuf6`m104>hsS(N3!UH4?du4-v8hqP|KZuN&#>apO0{CK6o(V%nJ!W_A>L` z?|%2QFTHg3?AZtRZ?{V~ns5_Qnujsukufel9M(3Lt|#_x!ZHhXTI^Q9vw{!B_p_a& zsj0*qg_~%H@QSb%UfPGvh0;^XJ3hd=%<6=&=)vhm(?q`@jmY|*1jneW7U5Sowg!EL z1Tsmjr4AQ@Hc|Dp#y#DH)2H?XSMlg6k?piWXyT|#v|(vBNw6b#ms2ywihiCsyFt&Q z$r3LiCvNdw|FG6|cXw5tHU2jMj{YX=pd*}P zHzFU2k;S1QEQS%kUKkr5tA8a4H)3aFt=;448~|-{cXu~8#)^#CjvrFiV{|L<$!S?| z0ZdIo*h-Wv_)|Fd;`)~AZK~CB(sA+(Od3&#(2fCr2kY_q)KH$!j@{+Ls!#~2ehtXQ zZ8FUG09-W9_QHi#ZT;XI3?-`5GSNbU71W$*GVAM_2$=`S_SY;G<1T*ZoZy!NnG6xw zd@1r^Pdi_oKMMFd;oBjKo{smP5t@|y!pR}D#j)!%hpPX(U+?_`N6|Nu$D_qeHS(_^ZXfTUL|2{Oi6EVZ9R=2x4J5- z2y)vyl-PM?!I9{DtmCUjIp&&CKhx0ECholZ*!ig4n%-Yt{z^_x_WiK^fmCGbc|2DW zzl!7Gd-!~)1T0rtf7iznbr{z#j<;B5&SWn)*w()1_TC;&Adg-zbbq+6&>FzxF(Apg zD0!XO=bgpH;uDCXM==ck#xqyGRT{%DJo#?z{jya|#Jj{xSQAJo5iM~#`Ze_Rwbg(t^=CwZVB9N1 zv>AM`iow$XhM=jej}i1GT19}~sv-a`CrhjlIL~8Q#lM)M|L+P|XFL$>IX+eRgbs#H zfHXs0u0T;y;s~Q0w={5=PL&?bzX1`RfGy)fBgofjK_I1;9uKQ-Bysq8N&#`Dmyf^L zqS!^bU2i4j3p(Trg4uF{i6-hOerS-N7ICK(pC^J5)1J$}UFbtnj3k$7(97la5%do@ zQQzWHv@x@{+hiYQS=+w8lO0p(d|zsNoS!d^H7i{q2RRe+)^M=|r<+qT73qFze;$4L zKQ0>qp<^au%j1*r`_zJ3I>{SX|BTntQ2m2!R9zr?b&U0soY$-4w7wodAL1O*&pt-) z<9;OliTQIWpnbAr;b*awueq^R3KrUZ?@=}DR#ysq32eC;d?5f4@KdU%lCDc!3!fgk zpxXYv3pz7zHQXS(tfy$+s30r(wg`@NRiCZJ!7&xr)ai64zDY2WcXWi^TKYVPTrr#X zJ#qChwfBjS!6z%igwqZ!reoj^;G7(1|3|`CWpJjp5>CQS-oU|eS7dcoQ^tL@`>ye-S}+~%|i~;GNE6!iSib_X%z=ikxN|1N4*hdm0T8kLTwVXu5=-mi+`yFV|bm z(Mu#Z%Yt;q@rnq!Eb@==n2^}mgo9Rk5(?s&I~8A7)+F9>aiw2v_4RiX)U{RB)#K!y zJg(&$+S*0r-{ZNT&>J0ETDm@0jlQp;zUryqQ;U|hJpoFC@4_fd3=+q+wKa2{v;P#y z0UI&rVes$d;a*TG!Uy9DJLc-=kN1h~+1bb7 zTquE0TX*L}XYWU+tIf_A0AU*kBVB8>bMSh)>(@N8cF8Ao=Wh^QL zNIWlC3;bD8-1b9Q?Kzr72cbkNx2ijFhjI(awFdi{qvR3c;$ARz*Yd_Kp8%YFlGcj<{~=4S_8U&)4Cpu zJW)ww|Bd`s073y27}&ORDGWIZW8eGhG$*FVZn{s6na{ukV4meyjdOMmXfJRuo<3MOq|Es z&(d$e)@7RTfH6J?RsDUo&vJZ{`vupjHi2yZ>{QxUCnFb%1@V%yYq>sPO9#Ww$=weZ zA|4K3$B~5Licb^_hq=ztB>7)g4iod~Ab|1I^DxbwX*v_+9wY!|#}LPN8Z!L2Hj0KY zT2rH5w*Oj7T4+Oqvw#59b;SO3A$_nwh0or`c%-7b~IJl%Ietm%9 z4a94`JEqzk%c;m1+86J}fTOffw(9UU@<2jHc`dz#c`KjaeP7+SI52n9x}Ic-`9tcu zYH!z%#OoD5O2j_{tb6o>H%ti*ryDkG3i?ywbBVN!Hxp2C4W8kIGRI1CDckxl~v61LGJjcX3 zcZ>l+(qrQZ4kb*GN%#t~nky+9Dko?Xz)J`17EzsI8lli|kx>6#61*ZdDyZoz74cdd zec_;=)>xYi^7zCNZ>spRJ&(m^5tod3jtAC;4+(Wv0<`0ry1Sv#HCKsd@l!#cL4Ob0a^t~%^?Nw(N6{G_9|$Djnn+K(w)S>PW5Uq7-#Gpfv7tqY zD&-Pf8nWkZoOHW*fhjS_ps<#x)%vXl3J02k9xT&E&}#TAsjo~@R0fj~*1dXAA5%~`fkY^DeshFbqEfRPnVHYn)&>$=zV2mHF#5|D%!rV?MP z59wQaaRq%UDcD@s50WROcx6T>YU#^Z5|B()Bhef-he%YJzoJfH+k5}BO z^;M-B}#lYHH8pYHRdtr?cYO3aJ;t=@P z1eZyZ1T8J~JE7k+i+&lmqU0snhv?+nU67ZVJ8*uM=C!;rHBMAq{TEL6|W z2-8`dVunjMGm$t=kfsrcCSI9Q<6*Ujm^U+noY<;1Gre8 zxF5p)6Ou23i5&j_Mxg8#u@+^L>}AF(sf=hJ(K$c#37mmmyH{C`{P?vauTUy5-}46l zYBX-kC1tPU(ja|kpQ&3pi*%X%)17ulNH=mfc2G?e9SgL;9o%vU97>sjh!Uze6@0Zu zy3NBP*#S8#GNlS^L|=Fq?b-Q5uZ%iI;?Bi%B#EJ9yl4v?iIDvxnm;pTSWcUIoH&GH zgi~;#^5T7D(ZX4;*LeD0M6;o`qdk6NF?}qqN%o1cOPFB8NLwpRU2CF*;+fCOsb~HV2JS(;@OqeBU2rH&W&$U{wc};V9 ztGatwy`*etmC{M{3hpi6q8nJ7@&j;`LgqD5>0vS6hAI0z-(*FJ(ZYf-chqI((2VRt z!$Bv+^$1O&qxb^UO5Y#-`$95_k4$pW70b)I;syxkb zI~jURDJlsShJckJjP6kqOnvHri^Y0H0!54(dSgzSqg80c+t-U@7F==&%YRZhfsqX&8S)jV;F%DW$V5j>&G}_+7Rz zCvMa$*T%`KIedzCnXCkpL>kP@&BN`Gt0B+Bg|%+$v#C=D$0?-(5Af6KpIiFzCuzK+ zMJI)f%3nED&XWLI;KD-XNGQEj{q3PdkPceb_T=xK2N6CT*t|@o8S#@0OthW z`}G%615m(Omo6I-7zlbC$gw_T-yn121qjL%${~nRTIUW9dUp)`Cz9>}`pb(NP2Al9 zAE;d4NWLBO{2Cl@&_e`NJhjPi?EQ5Il4-#57yip3_^S$DA|Bx=UTL>=cxR?9mKG73tQefUr1+CGa>8(6nXb#4&%VJ<}(gm6n6mS)Z0HuD;=rPq{VDO*XMULcG^eJe5MVXb7hk8-g=|7G{ zIk7C6DItRSBY{Jb@Sr^77=j-0b0+C$R9%iQ&yECMWH`n&%R=;eGoqcKt2&IO=w`h6 zr4j$stcqo|6j{yKV;IrxRCsghg*3nL+5_k>rxMz!p3JYpER+V2+=VHy&Mto657C@Y zI0W@@Lwmgt-y1qBM%(d<1*lGyeN)K4ShTYgkOFM4XhRY}U!_dOIL|LFXUhMORoIIN zW02{mz|lpB?~21jj0vX96AT}EY$M6fMvawvT|If)S#pw+Z;g`e z8XR~GfT_e!c>>wcJHC!suN#SKTizKD$zXg=tk3 zF@H;_G6=9){h2~8#a%yngY%;mPlTOaN)mz9q-g$YOs~wt=E-ctUP;ljOAHg#nG8|a zq(fS1bvAkkdO%dbu_7L+{ZFx0~r%gl+Tiynnx4ybZK`?MTW>(hb4 z+=7twgb+#M6jKp)A2%Q!1d@C<46zDLpiWXH{$*utTwl5Y*-eaHygiM;QFBbbtY)&a z4ggA!x3anFC#9Rgdu$D_iGY|G=Om)%3ePQn^Zn&AA6fr18z%6paui=tx!!#64^#r- z4oKV|HSK0x)*%HEzD0D`_ImKnpqgpjjrL8 zxs=0KRCZM~kw9+Q)KjX*our}ShO3_4vZcX5NidfvO%P_y3wY=!CZW87+PiMK=h8@I zE@lqS1g#qRJV;^rqhl30Q#{z=`fd zkJgYNlc$Ah_WDW_L~{P~3naAjQaUj;#elZ7w;Sp!<%Gz#)&A8UM}zX{NLZdVb)8Hl ze6$C(G#wFSPE#0`B62i}mSTMvI_{G`>=XAI!JCp6#u4Q=A!?U#tO7jfM@ft$kOTY1 zLxFE@{tE?d69?h&*EF**fm>edGY6B%;7P_wCB}+8Uh1{1rzC6NNFK6+G&6f|o7>HH zHuA$ZE&T<{AmhAL=ndB8<=(zbGrmKo&t9p8R zc1}9fOD+gW@#2PWV>V&thdO^dWU~irkt=9qvM*mBSdK}_4s!2o zh2&e)E%(k_%&4=atE;PfMgN!3J8x--$v%by-ZC4CB6e3ZtIORx-9xqSHV4{O9TZK` z)+0c@OJxIbz5(1KN|#6%Jw~Jlyn^&`FT^fGHly#jV|(nroILv_L|j?(1!`(VO{w>S z$>}WDFiPm^J-KFdB=;k{#h@Ry4Fxud4?Qt5R|Ts0Hm zr_b0bsLDJ)Iz1O>3JZxdnoTA{KpWZgcJlFOt#Yvd8TIVO6ZYTD5br=#E$myVE1_gfX zOiV&Nrmr>7p{NW)K%(k?k+dSyp(xgv_l|8!lrva7ItN%k1_W`6-&5&^HS8WD{<%>` z;9Lt5L8EneC&I&WstqqUM-nOtyEd2Edr$xwJf*hn^|@HC?zfNFpG;M5-B2+;SZ}s` zU~VL;EPhA+8(|~EtF5Kg>HYC+w@U7ORDEH)u=R6K|C8`74C$ZtD}A)zgg@MSlx;Z2 zq9gD12VAqWSF)#j*(CigD@B$|Bbm(Mq#1U(f3qBQTzBFen(h&<=X5Ro=*T!fKF{395R?m2*2_b8h>!e zC5`V3ldyBqy|yCeD#>f4qU8i#LJO81la*OrG_p{3)_*T2`k$=3k;&{5{J=jefG$-b zlv=)VHkaZnwWQtggu66*NQdR!L`R~B%~aRaezZu0apc+wU_yRv$9;FSw~ucJ_B_;! z8T$elCZQj zwsyMMc>8?slk?q$ujq6Gs4+>xQ$Nq9J}!O^J!|Xl!M469oeG6-N41~z1~3Quzy*dX z%AghXz*lN`Gm84HjI4@@!~Kof-Z2hf-_{pYM{WJR(?vPo;1$=jGyvz9b%9yn2d{j^@35EEk#bT zf6XI=g!Xc5SZubvPW~%USxu$hR3ly1;u5T0O(2oMYUqksv&C(2yd-rJ?f(ejzNfZAS0#NZf~Uzc50zYgO`P>aBgiC%U2N(?i<6>Co|Jj=1B#{FO8kN`O% zM*cf^$svs+A5v(Lh86ji+uJxF1X7gFd2Qd$J@E1Uc}*^=6B7)xVucxA1Siw@>6tOI z%LLBzN|=!bn3B1=UCd}clyqlJpfqPlJ>I-n$G2^ie(fnE504HkaMWxnlXT_{5T%t} zH$)DZNujY8^ddx(Vm%gNUS`}eC_cYAa??w$f@}MAbDd;JZtg*l=6*6RW{hcF;7ys| zyo+{!`Vw>&j&!`QJXu5u|HaYZ1Yk#K?498c@_GG>s`--le56a$zS6DugrKCQzd%RW1^;MnZ3FWj+N(0jp(-=>FTa8k|kL{q+SY!tgY zT|@NJ^RO|uX-SM;tlnTD4-6cf68K@5DJZ;_<>Iknjdyf9`)ud`KHw)y-p_X3UfbR_ ze#0el0ad0t8j$uhZS}P=jsT;KhGu>v#v+2*ccG@5a5D9z$Abev;<>LRk~p55rQ8_* zO@Qp8M!*}@LbqUW_Kp0i{u_Wpk5k@9V=k=SkSWZx;UO;Bx)Et<`A~^rhGS)GyR)-e zG~C$O`!Y`Op}-$S_qSs|AMnTNY%f0F74NoZ$X?50O>l8mWOi>_S{fep*#&IMfJar9 zRmn7rmF*!#fv2hB4E+ED;>{t^O1+|UXv8E*gFfO+5}GS~YOw1-aNPM2@G zv!r4tJHb~GYR2_G+n6dW?G+&FSI9s}T7^8kAE^}cmcH~i5!p!SX)}@US@g-%JoCU+ zl46DbtVd_X7QefpzC9=Jj87k_+S|VBZ7FxXyKHB8PixNO>g3|dVU$9w$MfsmSsyw$ z7e2*17b33b-{bH|c<8IajIt?O7~Sx-oc67^bZbivd}`n$yVa+kA)Bqc08A?fFv&&o z_GOej3WWW1p+YbJYqRc0^VHNf0H6Rx`(IJDMdh5od(RG}w~g)VFul)R8GoDm!}0k% z6D4VxPrnE(bcqWYxzAauPdPKII{<-P-;WxTota4tKP$|({t-bC*oY?+Q{1r01~v&* z5O@A?`@IF|B?S3bL`FA7W9P2zb~_|M^JGHlpNLK7NqCHGFG|H>ohgEA(keWoqd0nTQ2hFP_armiFIp9s;Ygxx)jHF{FpQ4~ zZ`CS1%wzHyEY3rN{kKd^ORr-MG#f(2YcY}Y?NkNQFC5`oD|u?HlpvLn+I$Xl8XGB6 zK3tcw1}8Kny*@_P4g(*xspYZ>jNI531qKj5iIQf`>a{ob^TA-#x$W(pQo1MR+w@q) zMLzHMK!Ot2?{l1;-Mb(#b@epE2LjJMizc0(>VM}x#ohGz1OaVXJT#7p1t_bES43+h z1_8H&OOdNRq*_|& z27%E+y&+V4PelGpCo;4<1`|Y0Ci8lJguLi ziPqD%#UpbdtGAnVs3rE@$6T~;b{`Tei4##T$Q~HwOE9C%tQ_n$lvabCbk-LXli>>% zVb+~RUqkEEh$edEAiN7QAl%fHu5xNJH0uN=1Knjgj`)D)bc2v~OymfXZj{}NSKvNF zj&178##ICnccay(muzWkXq++B4=iBh3X;A(o{mK0(0hMq*+j368gOelLSv3Oju_f@_5{jlan@LHz==yDK2tN!_sYyc1b!>zDHr&QG+2eqZ~*SeY0m; zr!#e|032?$9Lr~WgP|z;`Q8W^lAJ&}e zMrZf6;|%W#5AH0t`*v&rgta-)w}o^dJsTevhuK}+>GtYs-d`cp+5LT{tIb%S$F~(7 zPisfdi-GnB5tl5my3O$34&gbzB2v%EgTHW!hn%LIV;yO5L{PjxMO)e%>;EQ9U^xE9 zsO`2%I+~AY#I96qAsA9lg~J(8?45yAp!+ze>9Q+ro0<_&;ZwBhR9#yX@tj@~7UocWm(maIR!>|fV{u>iy zr&JX>n>FzV$*KvbthffKgvoG;gl|YlZfa`Sul~D5r%daOiFea}E@HBmg!XD)gvTdg zPdm5OL@QiuU^C^O;_Y%v<|mzY$6>-aB{}6EKcqLFir>q?)yt)hv40_Dy;r}^r_sKk zOk6rr+kDH1MJBWL(cyKK!ID&vpho9z^mX!X5#e1o#ffBLuuUkeeODL$O?94B z(cjdz?=c0}NW?$&iOPOGIOPcUVFdj)p#MEp#JciZM)@Aq0 zh@8;XLhb8+w}3NG|JuQ@B%GpeL1wy28iFSXP!}>aZNb4_uQ!8MPu$2P^|V%xJGsM#ypWlR`ef*Qr*j z5IAwShCGGp4MVax^mOCe@Zt*6X(y*HuWbnM2<{Uozr-q~dOsSP_~FkD5vm8TuA-Nf zg+hzn(ukL7C9s_`vgZW&Ns?Hw^Q5|%GA~!Gnc60-(VRj~y9m}Qk45AmL7}5oD3U-j zi4074OXi~dl~R-mW7Rj!ST*r5TBTtqw7|L^+jNP@7Kmk%9^Epg$S}zAhxrY*S??qw zSU>`d#gCYk;@4!z;IycvCMqoM-xkNj*(IN2kru(1iXe+M2`!5$C z1!`Bq_61btS@%MD2jh4t>lLFie1&nW+S^ZGh|C zBm@H92 zjRUiFp^(Ej7)Ed)fXLBSYWyQ6M2!GeIz+R!qlZc)E8(V=w99+5*I`QM$prD*9v~bI zH%gX!IAkv{u^d=9x|>7tuTqIK_23w5M8G-l9WuO`VB zT$IC?5uT%f11Kb!e>n(-u6`5DH{o7iPRhvQ6X3H44;p4u1Di^aP~ ztg*sHA=8rHekws-K}yz(IR(E^KdCpu-B;XN10zzZ39S$+NSzcHH4a1?rx%}Nhbsvq zm0saI_+50_Djf(XJGsZkdefEOEh1NaJSl{oKDLYXp7!iJbl^ua?0|a3%-O;lt^kbt zn@qHEIYY?hJ}IRch{$aaevXmKT8gP;c+uEg-~uEj^>t;dHk7M!w1!m)P)KAM1U&+3q+{8%eRx@twW% zmJP@@l1l!$zARrWh*f9fdl&bFsCI+kb#}2Gl*zv)R(L^Z2c(P%`lL<&vHBP_& z@%r~i)qH##(cLE>GEr6tbUWHSa!`9%Ig}c10m{w;C5u;Em$sT*6WOQJzm5w3io( zDqjzG#{tRFga*$zZKo{u@GYVV;RA-*wJcGi)2(Ty1C7K{QU=DG#NluTvtp~Wv%UR2 z`txdf>b+h^M0f_Ov5fIkM?=C!W{@2=TVhDDx9V{Yn7Ap}&ePY5Ec;P5y@zZa$B*b-EAaVUwHi^QIF$`7MzeM+zPl0W4;CKxyXk5 zmEj}8CGom{k29t@xUP9*BZVNKJ$q5f6ojDUaaWS)8teXE2Ky8ly_aMBpQ_vVybTXo zm$V|E6<mVtj!go$aGdE%#Nk_CSmlRy~G7>|r!3zP~E=gz-B=SW>3uOzDP+(~0NhK9RvX@a{4NPu+n-88W z8BnBbydR3?<}iG4Voxe6l!&gmt}}xqmGewF4vS&(#>dk)qB_;@a1a}UrrgS45KD?= z8pG7!gsE0Fa-_m}zT@^#&93V)9{Ck1)yRJzPB3~ezVvU$`>g$h?;fB_xOiJvyE-Ky z>>+&d_kP|;82|k1eLo%;7@#0N0zIrOTH|kfLJ(-#d5zxrJ?!f4e73Zri-iz>v~kvl zHyTw}C=ek^&*8Zc#c;Ao7PairMApj2cC*vl+Z(CKs2-ux%)>4wIU`&e4oxd6!UdP6 zJ#>(*SaNiylj=eAj{4Na%o=_>Tqg&ES)DOHElf-YGOea3Lu852yFIV-K%%jyL8o7>;)Y;DOA z3SAnLpCS2N6MKi}T5_iE=SV>JTtXbgVqk& z0KA!?^21fGA;4lD?7)uP%s#lK!8M}8+gBTqfdVH3?L`YjGiCrSZ}E?!(erv_ zplcuY_xE#ubaz%aw|V*a{%f}DZSNLZ$<58)SX+bs(wn`IYvLwB2Xg|)ZMtwo2BuUW z-o>!zro;bOY&j8MiCC#dq0<sE z?G%gH@nv;^H0*zE-Q{vLvD=vY%>t)5+KJKe7X=d#vYQ`yMu0E03S}|`?N@)rZp$eK zk_9N3CKm7Mr8yj&T3j*kk7169o7EkJ6B@VJu78&;%`A@~)v z?N0szyX!tj_8@Re$JLLjRwScR`$I%lDVa%1T-IQvmJC~FJ;5HzaOxYs!PlG_`BYn5 zo$vhFK(4vK&Dba2Po6rzat;z=io^Y_I8{wm)uS-V?*4(m-9K&#$9AWHRT?i_OWUIj zn!@d6da!%T2DiCELFM-}*&h<_@EKg1rB1|~)&UpaxP?4O<1(?P)VdBqBag9x1(L4> z5}0yC327VyyUh#N4~9$GJi5HxL9_TLpy!A|VnOezgPd1c|0`~&Tzn_QjfI5|94*Ie ziLFzomkym}tKg~Z@7-k_dPK20%|K`Q#mly^S9R|!I)GIbgtP`ls zXVPQ*5fHvA(vFbeazHB%iDj~IeYnBch6D}Z5{pHX4Yd8OFALeJ)&N)Amp4sAtB%TN z{pPbgoWOU9kM|^bo9NkUyH)r`&gpbEUwl@+_Kl1%y3IIliZ^_?03ni9ynBfP*`Eh0f??PY6dusriu3PQ3fcK{N z=!9hzQG0{(NT4;JK34%zqGVlx9m8~zDM97s6Kn)|sZZ)e3ft32_{2e$ekzQXFS@I- zX`1WJ3i5aP^EYsBi_4bM`J4p24{rG1pGxQ6Kl&g!(4#izjK~nwFB2icsx8+jo~*#o zL;2)7s-Sv9wtA{bZ`Xx#S6;tSIBm7>$O-O{`J+}_)_je-S#qLnZaKA7>}xb}AqP4n zYG0laI={&Y<2r5 zqT0T(m_WbwCTVJ@f-z~Bh-3RP(r_7({qY$0W!tTchGyodv&GW5j-TmTXn~Mk#9({p zakp6sd?=?b08Or($h|8sl65L+}WJbeU0mghvU*@;YuLB`?;G^X3DL< zv?wxU7L%=o;nk`$9(`tMR9kLf00+Ix)b z9~?clSCLs#@DptCH4Bq@f^mp6O!l+UXJ+p28%RKJuCC_f&Y`QFI_S*@6?eeDS-!E{ z4>X5jC;F6ZBl-p9i5g#*E%|U5_tE`kioJ^rD)v2S2Z3KhCD;_?%mm;$Yk%pH$#VGO zV}(Z>;b(Qf$pg~a9VHAVlvDbA%Xdd0uL?vpbH9-V>T>ZNJv}phwmY1up?IGI3@V>j z`NtCQnhSp$iNN zP$vf-DVVi1e!^5LDfC&6=9-h_U+@&fixql-`8t#?ET%APgGit2*l6OgcnlT_br?=# z^&0dU5T^f|oPZ0NLZ8xe*))a-4Kmqz*)J|8#kPKjiLM)3A4AfwUMDPY7N6HC@;A-g zn3JuDY7nGJcDhT)T3o?v~3lTGB!2xs|UWBRy*hFsZb=sc?$;xYaf0wzjC#R-@1!!U{_oSUIYxm_p`}VEZ{GNK+RezklW^@1l zYKyoKRIwNog&iFAgH+bR1tm?r7MNO7)%B$6YC)HyE4&1jU>})i?^6X)rXGP9dHI+{ zp#JG%_)LRpN?T4ka_6u==JFT7{&`5h0DBo9)VY_E<6k9)QiA@+>gb-*Q-k2*diwRP z;HvL3^75zB&8bcf5;5YwpWmF~H%NURWQY=229|CKQ~u(-)(RutnNC}q+4E!Cr-)%4 zi)0|v8Y_r`ccPhEIU^qyfBWb=*?hsMWLaj`9V+$3F`94f?LtIASz1bE66f4V=EMwn zsNNC&AEd&~#h4uWZ6UAVNS1%no(1lA`n4jopsyrHeh7NMaVbFxW2Pt+MW9TIE;zlu^_`}>q&g3L+orklIk#z^)G0%q1BL_HHrqS3BRwmKCuVwdTDzUj8zA3{o$6NwZp1t@+r*Lq*Q zzwCHiTv>Q~KYf370z+Cpg~)TC)&g+qC)2sQrH0?j(U}szVnaZm--#pxWIfDGaJle< z?Y@mJACz%TyzFL+ZSnB%=1u3n{Y0(wZO}29W{cjz?8F|OgEecH%+e4;&Ex&$BP`9| zB|(s7{4G(Z%DToNH^s8iMo9)R{`DF}Cu* zfUZ>#R=@|jVe0Q;cZ7yfemDcAqh&;GvXWw&=-N}praL1%)qG!1c%$+PX_}B zYt-fhhw&*V{8k)?GugR}b^L2-4|YIWnTpLMJGb<%x;##@JvDrySRs8(2K#=2>)?V1 z=a&R}Eg+qO$o}H!5l_wjo3^vw z2KmK`Fwet_{oH^D8eIII2H_x;-G{XC*C z)!zBIFD54=H|YgLc(=QIyIVWEdwRbA^}fEjkP{Sd<^BZge*UxlT(Y;VYi<^qty~mL zR)InqOR={ z#3(Ywcon;WvPbq7wE&Mqo;qQ8n?S#CG0iezd!2Z=g1%5;^?`RaTaFp9cM4Q%T%C{u z`iN*Pi>*`sz42$^d47Lq5ggUKt}|^0%u&FDy7CiD*pISp{NLHIi4OYcC@A*e;NZda zZk(SI?vMzu_7AiK-{;&^^tqyytyE%}9@OK9f%mJkX%P%;3Sifgv`yg<#r z_E1dsb13)wEH}c@hXXq)%;XQASd7E%>kuTZlD1jKW$)`Cf0hNYIghyfkfpsjAjOe5 zZdUZ($_91V>{wN~3v681{W zd+adnkiRtH2$8_X2Vi9LI=RlaY2{X4yPE1mOg(HfVY6-tMNVeGpKAw*D*2JkXxscygP0VFy zGyE*)1N14N^p&_zp9&~ypn?YDqkhwa4JVWJ()?pylp!(q+r_!Hwc>FL8_;XFA&ov} zzS3zG^W|EC`A7E^m=xIQF=;`PwCP{N8}dyd z=n$BO!}vaCKMMhWF;CqaSi8ACkK55(?~tDUC4vgRM>1Jer0SZ?6_LBj)y1W^CQRS8 zEE>Jk2I@T1gGW7)0_zkav4mw#uB8Nv*?2!j^zU(Bkt>u)jhzk8PH|!X9D}M$TEE+5 zOYYk`4pp+zAtgSdNA7fM-01lAOC_;&a(pL|E^GIe#oKoty%av{qcq0bJl{p-PTpHN zooAPBjfNe4@R^^Asd00wB9k9@a3u_jp$&!GBer9jR!&6$Enkvsh+kwK1vIoKc?$uwuD* zHMgP}R<$2`z@8rdzM{BNmmmMJvemsf=uWtiI$?LkZa1YUX^dA8CPgGSn-ML#uY4(9 zD1E%^Jjd%yxGLKg?Ns2(D<~#{Kn^4>!F__~rSj&426ciHKI0vq*>{W7k%15b>P6y< z(i*}%W#-ZJReyqpPh9Zay0o*m{}&hQXjNtpb} zO#gcgbM{^GCj2@Yb{I2icd$sU;u@HE!@Doh)J&e(? zvOrD;ld#KFMojSW-WMLiYq@Y7tEsK_W)BkC{M7F_TzLt_p}qgENTE2m`~-LS1^H*m zt~KN~vk$9)F4N#$uyMZh(&tQsu#my`ge9+FQo3!FO04`R?rSY>{_?NSF)eEyIBHpE z7m)S!3z%>wYBAKjNH>6P=CIq!w~&zCyZdDVmNCC!0C1;&1i;GX=gWo`fjDv}1$8R+{tuF|1ie1wvy)q+^ z`Fjp+y}brc34EPD4zQn7zZt-CPy(c+WXzcw{p#dCT;fTh+Li<94Vi?8gp6RurkEAlIw>p!*vf_aqrtnnHzrYM*XtcuW~wDYiOI7rY@0jYGtF)z8a>932}V?yTP4+xjYG`B*f$w@C2!+PZtC&X z3gq)E%FIZQ(M=iW8r>1OMyk5oTkqH0`6%i*=PUl*Ey>8#(;i6ZR|3jC4ymO(hLpYv2sMzQ2b%s3izgD? z=3hkW|MMFx_s%GEh~$E)CR?jEZ_5gImKWE#y8*A!cWHQ(@N)77k5Q!jla4+o*cq?K6_Bj4C&l+sO^~L%veI00!Ab_#$7j24Oy?b6 z&l!y_&E9qCCCjN2D%4sZ64Kn#-|Z#qLry$orbp$;;yO1$Rmw)M5rtU`stt@|5@}%4aM}N=hyI%j+Av zQD%8}Wi;`@Z_%th8~Gow_4<>9G%f)X`3VAH!8n9}k1oZ6^tB=i0V?EjQL=KfLrU30 zf6%?cdH#`xmUi(Pb5grtiSk3XJs9X1UoPsM+5k4pm1*M{X!TBB(R2Dk7qnf5#JN-B+t-jle9Fs#1{ zEGz<_c0@6^N|Irfa=c~n>EeV{3ow~xUtjwyP3P$HRUM7A@{?~e|3qY0Ig%T4u+*4R zzmn`Dx~14eRbsyHh1mi`!e+T-lKNsC?`IJ8D3(gFmm;&yf@tS60nKl-%Y(KMnj1y! z4kqGZxw1>zSrVfX$yxQTzPoV}N>(;Jq6=?3JI}mBe@RjW7SZ~dna~AzpI?lNE=M7f z#bqH_ulv)R?&=yEIyqAH4qT*A5e&r<2zxn2*Spru8&h@kPXd=Vr{~W`?gsD22TCaf zS>P2cPxNuq6B{F-h;TVPx#92PodpR^G(8~l*mTFjF){4}TW$x{d?DTnY`4Y#6n2CV z{??L>h%~Bo&RdrVXUKI*4XAV32!g0ffhgu7E-PUn3{b4C!UVb*`M6|@(^!u#-G(Fb zXj>7`r`5bU&_4yDdm}i7URK zW8TB`SLPoV+r4vB3~8G;wMZYuBfW!B9}MT?vLO{1t!v)EBW+`lne(3z?nr-~#+C85-}Gba$j zO87+p4tAUXqJB}o`Va2?f9LicKa($I>=P7F{#~{t3<<{bFF+gdA1LwZV&wb-GkIY* zK^)FYCPjaldr;hpr&pP7Tthx!bNN5|U0kl4B^ClN1jcbn$LAcd3^PTXd{Q0}hQ_Cf z{=r~i@=Mdj>BO27^UzwkF^3+jco*}8Q#i;e|9eYE-uzTqCXMseH?kc4v-NTr>JHK6scDY_w<;w?Hh<-0M%E!mH#l_);+iE2GT;oHAu9rfBPit^{Q^U)GFr#=$lxnx(h8uHyFF z^w5QJx zxrfjlZ`_FD3L*kBqbZ2MoJI7jlDIN*jkM$gTqE*09}@p&@^hNOpNyNfuRZ?hKm(H5 zM+cjzT-r-wv(jnaks^J;?_8REq-qIOanFM*M{nI@5 z6RBW+Y|ij)e6%v)rH~a{M!2`;A&;%5J0HW~%+-Qd4u$@v>5b?MCh>T4A`zc1ygMZI zA+G(WlF8=5I5K`;6IFBn+Sr|Jj6=EGeQxk_R3c(}jEvd!aj7ZUPq8O45IzWvkIcTv zj7TIkgpB2LHW~lBZ;b4rIbxj*Z%+I zr`rNnFTIwk=t2pzDiukqYlnv{rN-wV;)LmzWMJ-+Lwoye#@86eRIhfa>1g|nNT^{r*5K>2dMp6X{ILfVD}elVaq+hf1ra)$b@(%fbr(#xu- z!%4}0JFOH3ac7@|Yty-WBofQ0IpZu5pHbu0^6ryYW@9R?4pfqBH(a-J73<0=C|Hnt zkGDyN!o#rShY(IY+Q?CPqU8k=(LoQs&-1GXHGeR>{jI8B)efyqKKGaB4cy^knICCF z2y9LjkilZ*rX`h1*CvVH|P?{W;9;fGw&aJC2+wj~5DqILwQA!c-puz#u&+gTNO=Fd z*^M3g86@6Crp$+}{)Jk3PA!oVIxlp^`IJ;E)lDv!VEFmpq1e5Y;^%Yr=hN?%@TV+t zTpL6tggl7ul_?UGBhgOv7@?0PnhH&ST{$4|xGk(s!9$8wu&A^2 zSpb&;$KTCY9 z-*2Hf@0TyBn*p*niYEFaFI*w)13d{npUsL=uK~8!9`JXk-Ic{q>iMFIk&*82pcywW z#d6C6b|*G)hh=|$q*O#R+6Xc#8oI6$w$Vb+O?-UxtM(%rLLXVA=bZoDqW(yyrZvB} zBjEE=?NgA7J;6LcdW&@c2{nl#OVlU(0>UIbjfIHIPa}E7PJ57uT)3r8~KY6r~Jr4pMC}Hc|(U(v&3R=ch`r zO^rxz&DI>RTK7tr=>-^;qLUxT8aF=Va1G$rC^eq4VQ3>N!M+3>#JMq>f+Jg zJ`V=A4zd-}8;ujAswKU@LJ^>kVOm!n76vT%A2S%g34fHCf3dQ2DF!TlPwo79+*r2A z^LBW|0KUbw??P6CnM)IeNy>b~W5mZ4(tVvq8tG5f@Ur^buUIpo87jJ05?&R^fGfEZ zpmApigPe?o01T4V|2cp2qUh;-d71SA`Q}jGexXLKj?2tw&4^XfUrrVF9`PJfA)4|9 zit`nbFFUb+SJ&oof6&~zOQNe8u=NLNp*&P+KkdQtcLZ(GoV~mUlXjQqyP7-{qeS;_?-T;TB)^}S zh*XsMKKJ`f`s??l5Tf)@MEEC{yS=rSJQw<6@9p`q3FQp<=MM2la}6WU1bvj3EAc;5#dl=W+^9soeUpeT2r4`?KMnB z`-^c|_UUA1$6cMf{$kFl0(fTY;#THB)%qF2gK?~$FAdfwu+Cx#tO2X8y4> z%jWg-dGn2{6g`ovvwN$qC8+*{BGL(2v!<@;JRXn&+Hf()V&mNDGZML57Cn>O)zxi* za;=75yHkj&5qBcA!@|c?rn+j?yy=IF*r-4^XfpwJb@%V`_pj;%(HLk%x}$6S13%OZ)U~K@psGl%3uI$2 z^?7M_AMBH>Rcx4XL{XLUZpQiGe>Ii11Umh{T|n4K0Ja-O|5v)jYlc5DEslen(=e`31VThxp1TX$T>3XwM*6m0yI}3T?4&Z&_B~m0bnL0hO8}s2veuBPcLPR z#01}11t)%MuELwu`5+=83A?G4m6faO@?pGH2WhtnZ$|T%jk=`mlf2#q8cJ%uqY-4h zOa!BRcqaL*mZ9gEIi@Fxwmk}ZpibxrVeKmxdLH|zdbCH*BX<8E;kZF{krPvzHmvk& zyxOfpuGtpz*@A3}DN#KFJiIv%6d#!Cet8zT`f7zcSC%43-^=&s%U^W|Mu;#B0wV^F zlDR|~36Uhw*W*#EiRpWj?OdhitZ!(uv@x46FYNeqP6qE7)4%8^2mj>#kyi+0l#_@T;CspTPF)24 zsQm?giYvJ%jv$a&HE&D&YcMux$+y*i_?sj@O(S+mH@;@rDagbW%cyh^t{WwunpQE| z7<;yeZ&ey%Fr=~w%?*w=b@K;zly+3$JGDV~Qmk7#fCR`J~MUGK%64j$&fZUG#$t<(BufiSr znmnC}i-bo>&S??gt9S<${Sd__^EJ1g?XiJ++EqWaw5-K7+9f`k)NOI9dt+gO6 zc&}I045mnVfR+IycqFnYz=~WpxJa7+itFw-n3%gA0zn<3-|OI$h8I8BNB7J7JaHih zz|RX~MIffc*^2m~1{MsJ{G|I@uX1U2%p(ncWJx@(6S3#FRcj?*&#+iepXlYJw z$Vy+*Opc%4IPSyII6_52V+GVpq6hMV%4ljxC96SfPZ%$YtPXp|cFo9%FJc~LPN$K1 zT-+>b{fct8AFWQFR=BST+PiFR$u6jPD$J`uluGPb2x3hFA7b5vi@-EBRo!5N;koy> z>lI+_*17%9dhqFt@-?*_vp0w260L#-WO(_q1r{ljz+{rCrt>IO_Kc? zP4SKIMTMf9+PNiUec?4XtVAbSoJJt~4UlPsNHMkJ_`E7SxY*WKXDM^w;7F(g01X$8Mw)|NIZM23CWd7_MRQsc5n;f=EvJDBN(PN^ z=Dw-?b!S9C;{iPsAfe1Cb3UC<<%-5JL6Vi5>-(~9QG&x#LyN-N4ztjeZt1QaLy?ZW ze$mj`-1%mRs!<#S-(w&t)l$2E9;x)FtpdoCd>{dji_+FHJFhq z`V$?d-)DDEq;;qQUanLW7GcUL*-i!8lD|kMy(LD$d74J6 zhL1`nOHKLxJcgtOD9D`B($vqbxecM`25uN6edapm)YMh8qw$ifv!FtF&K2IMXde^I zBas&1ErsYAXOj9v%h|KYB-a71hRC9klWxcw^)UXIh&aDMOr4hn8OE>E+b*zKU=0ns z)=lR|8G#2<0bvfm%b3>QZ_1zh%b$H4umZpHyw3%T@ApN{ZFUjg)J>FIJWY*i{d7sstR4^sNnuye2-#LolCp5Pz!8ieitFe zYOiN!;Rs~o=Y^mmaH&lB>;cv$5kTmiO^XX`cW)H%JclRwF|el9Mr-T*Y^>3d@X z$7=0qsnvc9tN?aQDDw*7n*$xDFDvtvCDEnAdTDM(PqqqSnd7DNO}Fb$u9Ms@c_aSX ziu1TVqUhA`7YfS@0vc~V%5mOCnM_x0*s@1qvaE;U>s8~BlMtM6-cYUvLJeX>%k4ne#Rz;5hISaf57EE zYY9ngpph}AysCD;s}A>gL~UBrk_ZtI`(LfS|03kqOmt+DW*{_lM);`~h|4xg$SCQg zslyy<%O}w70;T7jFX}?{PHMCCq#aME`N;qaGsS~gtu?}rKn*dqtahGUTu%MLy2yZV zXNA zOdz^%<;H)ADYlZdCA|wJrWGtJ5Xt~$aq!4iWAajf8QBY6O>5=4fha;0wS-Si!@?Px zk={56x?ck)V6mfxME!++UIdmHr+8t-x%KzA=JU`K-Cy|p`0j3zR7YdkeI!eWzJu<+ zQA8Q)8&}G0n^M}gdT9*e+Uhxzz;527z}{x?tYz#`Nl8!C{J9VVg>?6Mw_T4jDU+C% zjZy!ma&RsjmsPfx<&6y8^T#m$*>u4f|@8D=S^M&(^9F=FhHrguy_MNAftcw1 zi;N%^Ay8K*Z+OlKxMnW;AO!2nhY`6B03~vwyI(UhyWE_ddu2=`oYYN+!O=XOd|A)~ zp}6`V%rk$UdJjL5MxAt!_?5=EgW+$_2Wpc z5Bn54iu2K+!`APj@?1Z<+mPs#xlH77G4K27qWu|Ad?;hbt{2wvev)NBK)93f4Uqib zt^d3)dPE8$tLA2d0DEhZzNlQlef|IYOI3)lo^Isf>Txdjp0x;h3YwOQy#u#mQ7-ou zo~t>|)A7??J}Sh_djz2;0)l)#AzUwOac4|4IB-StlZ@8U~T zt`{5xg&K4U&4P=a9Yk;w%`IYwS+i#H^3V|ow1-DlV0xT*yuq)2SlTCjqb0>zeFblM zs~1_1Mo|O}_9orvA_9`x0Kp+j#f^D(^y}Y!DH&mOBEQ)ya>-UKEG$3;DyvsQizRdr zOA%zQwlffl*8!=U;>G{m0t`Y3qY6s#g@W1xEVH~tT<>W+$ig^L+TDc{7$+F)9PSvH zn64=?56Dh2Si$3?4*B8)g81-q%#leiNHw#j!e&_cSoDz)j^knKMWhzQP9rpCIXz?L zt|ewZxTIb%Hhdd2sEQnRg)s~997*C9wIXp`e0-fei$M>Q; zMp;_90O7|{*_nf{$JWLc!S{y3k9+v!#?E$!Z>N`Y6`AGI&(5P7HzC@iEr6}{wyIp$ z)y{W)!0mn3sZLY1LcjtgpM!eZB>=wZd&|g$9#HB=?Zc6~<9$ zKQ>6RsFHadZe)=y9>L(^;y$hZr$fv&2ArCVtma!~AT%X4KcVM9;ypRjv(J@aXP?3_6Id0vn+#WZCmc6a?{r}{e8AALXVQ8jZ)^^Qqd)gfcmI5R zF`P9y`+@Fp{vKr4%i2Z&YViaR!s@KS+U~Bs6NyVz2*}vFLwrfm6s_RhX1I#p!n>}P z!6mCA!RO}gH~T3lDMgEWIA?78$Witx4nCp|3v7;hka*LWQ%7J86)ih8xmsP z9C*^m{tUr$%Xx_7aP5>dI9D#iJeiCuQrREup(c|-qJnL4QvH*w?~rojTm@M|byzC; zUoUCDVEM!oIta|k>H$eP8Qq5rw~meGJ@dy8>`uO_GS8`WUUmk000wfx_t$py zV*YHtrJ%1wCITQ~{;wwq=0xW){JVyO!CBr`x0}zS>I>kHDkE-f1O6X}L;MZ(7)}Ue zZ3~c-tK`x?L`Guw@kb+)@yMGY(WunRdq<6yxVxCMQS?Gz#O{Otlq4_z%3_@TpH0Mu z$1$*4(8Z+j@by$4Wk-@^gbcaezf8_F%=-HKGr=ErYpW|rcW~ZY#60$@=MoQ#+cqev zKgV(o12GauFy0dyL-G`*yGAv!ZQNXfcC$$ivO6{&*z<7Edj8O>PjiZej4izeBKfNp z2v>7T4s(!TEYi{9jl@67PIVaJ+1lGL{w=4P{7QhsbL^V4kqDHF<7H-6TG14d>NY8q zoY98kbF*4$D;g#~jQdgwp)aP3#9yK?pOR11v^(7*ZGTlWC7{uR>?`c%;_1MTA7vz- z#SK$9y-G_eONyFvMt)^v;lV^6fBpAmUa zb$}fgz~BE zO&{?_xyx+cVZ=RBZllfdBqiaWH*QV-O>wCelZc|s4hl9=ttvrC`rYg2Cx0@gC$}t| zzxx5j&o;Bb;iw+fxD=u(^Xw``k^;HJ4%FWYK5Mx*6ziYaG)VkjVI&US)yF44L7prE z&LlpH8Z&kD*=1@!Q6GqQpm-*RWX`w`w*X1JmL`1pb;#enZY58h)?u<%r;gISwNIb$~QH!!vJC zoc}TBY4di+O1}8yVp57QK-1siL|zf0OkQ}>6h(C-WNH29%@k|~?$ekktiTr#k-Z8E z&4(lV9x?C$O~fi!6J>Mvn-27;{F`~_v^^i50Wygf$2OylnOp|;uV-E%FL3N$*KW)L za@V2}m>uuHPFPsjzuVn1xota=0W*i}31WmO&4|TC^iemPwVKm+7v7G&|DWQt&jRkF zbfP}Szx-y4PJA)buY{h%s2t3>34w(zmQfXgTFJvm4${}92*9})gJFwSMf2*(SGcwt z6sVF2(%B6oeC_U=JKXU0`xR({GaPgNY`A7Z4%#Jm1!iZu4hMZE9we5tj?}1C8Ph{afBOQg0z0aMr8KfH4oL?&O<~e|jNb2P5ZZ%jNXK+P91iE! zFQD1N;8~peWxh$z9pczAiD*!X1+^K3%h(|dp|A+zrK6F|8;KLv1I6Q z_e%TjTvT!F_WXp*`sIFm**@M0veoKl+7RBP(G->05fU;^4LzQ!?|Po*4Eor+Ycy+L z0FH-iaI6 zbDBN%&s+_WD4sY3O_)3^WOLQD=cVhE>x8TM9gf$-T;DyXPA%)4J!l_m54b&iM;DTu z77x`&zNkMwiXHmll-e1XrhGLQphfFVcF7Non22bH(PT!6MFOFJ5>;l~`#DW92)1lM z7E)u~bHXNseYM!u{>@NP38Za%kBq=o1XQ1WXlI#)Or+zg9aG`PAh^2EDSBTLuYFzj zD9+4Q<1@<8)j!c7Wzonx`Sg3T`R)%n7C)-1Dpl!gy{CD~IZ#l)5>o!**31CW2%8fFFx%#3=3!r+3yKvJTA<3SIZCGZqJzS4P8Q> zdbm+%GU`CSHECtg;P%z2IC#kbs`wZfgFJFY>?<>HIxzAUO<-9?1C}!mYjvZq3N{_B z4DcKlv6cimS`XT(e5S#{O)1#rIAvPZV91SY@$SVDJKI)&|1A3Qy$G%s%0Z(%99#&Y zA|;(%o%F1%%OxP*3xc`^c-rXgg9Gxp*LGDnuw)}>JF>C*23FW*PYX=0)(@U&51S^- z**rdpNhe?5oE3opK`o8Ni)r$m_%oG=v{JUNzIbR?UrJOVxy{YZ!0`mzv8H;9*}^AG zR|#R$g6YoGEnt*t3~4Gxzy`=S$(bqv#-a-}=^{hNa4lNKT4*LLe+sEvp7U zR}&KxfSI(hzL`2yKpSx?2h9u`pg%*EY~ik^ANR=a+s*?^BFaFLo_Rj&^jjlFh=2+Y;hs@hZn3VF za`t~kMOk66Rb&?v%b4AmW_25(k(Npgnb9Kd3p7;_!h^uOiw-*9$?5#nDC-E<7=9SY zq%5y6IC420LjK;g9>{fW+^8ndn4aSep~bby!$buZZjM8CKQlA)?Xd)@L+XXS;3vW) z;qWI#*fcz^=VgFP`?{EZj>s%jI5~J?5NaIRH5Q}vnd9moWpM;3xgL7%jl*YBkv zejH=kFib{+lKCth&B8Lmrvhp|k0&fNujiAO9ig&K!|)mLNU{_ZOBdv|ne=Uc-|x5P z)4$zsBbQ5QUwT7Z*VlN7`u92ZU$akMtSBv#-d0xUC9^&!C29J)(FZ`51u2KC2)lW-G*1hv5lO;02nG;>%QL<0ZJth-kG>1fG{p@a>edYxPRHcpF zqj<`Ka3H{zm1s(7rLd8!$X^mx6Ed|DhvDVj-Kc+cUr;Ms+9I*lMA~X@F`@q`R3xDJ zEhbur*AV<(pxy zeg|=D%ZHH@P>k^w4oiZoobsk6YOKC;WuHT;>JKI8qvR7YLt;dR_O@m*`B$yIk9-R? z9IY)N z-zzOwiLgkebW?naYW6QXB|OP;N=9wBMpN#bdPO3u?>m)(%HqoIVeUGP)_b8DvTa z_YhZ%Rl4WRUrppafq#}G&QH*Sl4yw;RnFjF`ZH6&4AmAUtuTk4?34?|(`%h&9!yGd zoCvL8J5<)r9#DC-Id-UC5%wrbT%DTSMK6c~edryAKua=*VIaRF;{7FH#d&aH|HaNw z8UaoH47z1I{jSst6>T7M-C>Fy6+P0by+-pq*Gq#1)24$jo`%B>rTo8Lz=FgzI-R|F z`2>PAmxV$w5IsE(ZJ^B+zB@;t@Fah zlPzL{G+Bd6p|82;ti$Oza!g_PJeK!wh-J!m;VquD(XaWO9Ryy|uCZf$0_KE4R{p4{ zs7g4zltkdA2k|1;lc@}z*4v2B1XR(px%JM?0t{usijam;GtHAz3vZwKvk1!g;S+xA zvU{~{%+MKWVB) z)lQz?zmXGzxtxf%Hj{uU*J)Scc}GbytXj{qn$es`Gw5Q?U=n~OR8!2Vrcll%%uREj zWi^OK%Y?=In2&^lpQl_M8}Y!A0alAuvqUBl8=Q$i$2Y?tB;k<&tZ@%8r>xZi%C|v= z8a|F#%MvjRpDSHcPq*@tD^di_uJmKjF3YlP@IpcOBpX4JL_pFAmjAk6vm+j$o7KQTwYEUoAF z{4<;bXxhY~mS}Kh5pxMuY z)R?u}0elr#-+IKYn$82`)nVBdHQW2Lc*m_;zX~GftJny2_+&zr6NV1ib z^Ym=MMz$CsYf`+fcEE{WxHAelRP+1H)cDoil#DPMMI1G-m%eo`)$u5s6G{Ny-2R$D zK~PL{-f6J;pr>U%H1<;%81H#r)nt^*OCQnSY)*~fbSPLdrO&%>P-Ureu`@`(cwtjz zaem?gvtUCVC)d_fi-E0Pf3uR;A4^U#^WgQyNtJKq+hSF8V2PIanxcacQ%DK>WO zjw@HSXC?8Kr>Dzq*4Yl-2b(W;U-Hfl{`XmKg(bnmW3h~<+VLGf*Qc90?b6A%YFX8G zoQY`f$GTa&Nu#BoS(GZ^<$<{#2S1tzhw##B(MdleHRM8>Z!CNlq)6iEBP4z}6;GEW zjJt$5TLEnY6^hi0kGZ~~>#Oyd2|*d~;5L21w&IBWBkoz*nx@1pyTO7FLU4UEweP@$ zH)L0fH;exP^~OTy?0Ow7|Fu9$?Oc`-#yWQ(D=$h~ocKK&QAe@4=E~k?ta|IXWs*Ep zS*=knBZCF`NCs76Y*9adFz zD_c~icQODX-Y}e*DR&FC-z`iuR1bs(Geg@6Nx{GEOb&D>oPLn zU&4R^ZLDoP#zY2%tvfk7s-@|tL_a(cdboc~o7R6|o-yqeWGGb|E9m#^k+br)FaXlu zKqeAco4i2+kAE}^0n}^5u|8`eJx7-%Pl9a?pt=%yxp8DI7r6C~{>gLtV_&YaGPqg{ z?T;fjMu5S|6o!pqM+}#&z%-+uZ-G&qQ%Nb0vYSS9R9Y@(tDZ%go~wgFP|@0&kG3uyzX1_ zCX*5wr82cV6}a31?xo%FFe1OSmY4=omO4U0$XoEl8kj4Z%U4EVrFvwA(~)AYG!)K! zFU7_We%)Z6j`S<#5r{@@(d9WF$O`ndM{;jg)}1yS%b*WwZ1E(@^bZLC+vy%{sVG$R zY^hw8BjrGz+as>!l$p=n>33j#u(4H))rzI(w-tq@jcRv<|cyxnoLZDiY|f1u!XPabYIw{>)jrRa9|0QTVPQKvBQ_;~B{w#)dV(%4C|vUv_cvV-7+Ry58(t%# z|GLlVQu@o$jdSbdwkQ7TIMGDKfNMO(OQN}J3ld)ziTV~qm-SkjmY!r-s~`0)vf<9~ zf_3et=DaD#$m4=g814do+@7jaq%y#^Ej$(25bI9P7OL>5I6#7wXABAW0fa^&FTs*H zIdEB?tn8UQZrV>Xudyo_#QzmA$^`JWc3JD^q>_*S;o<};#!oIP`G0aWRYj`^~{#VK^MZ7xngfkf zg!fBk;K3Meq&|)5M*8zRr`U^zG1-p-o3>1I9y0P5YcfZ!ms~edh+qxW&%#5dNU!j+Q-V*+ofLpKp!Du~6jzu{Njk$yA99 zplPFB*>{ET=bkXBkou{z`1QOYzW6xYQ~!d}f;_3x1H_f3IAp2~S85(#4`r^-=*mD_ z+n*-m*hR4CZUFXx6Qo;_{H=!Dq$A5KTWmgIp6EH`hME8X5m(p}{&BeM4}$dj;_&P3 z?DYO#m+Af5?8P@9$+GY9ToNcA?{++fdA9k*o5Un8ia+Wo|ZQ2_jPGN87`c;<=`S(Q`nn5tqI4!Cxjf!508?1qiM#RdvX6e zxibCb&}iTBAqVXK#4OxnxLA)^Pem+0Kp!H;E9lG0pZ}`|2VoRIaQXc|n%;rCvaaje zO)9C_wr$(C?H${;om6a_6|-X7sMt;_w!VEo=e(=6^$%8?Ys@}+zxoJu1O&ZX=l9WM z`bnCyyz*Tf?^W50?htG(Vd@9P&TMn9X&wCKMabS*p3-yl6`9D zYCUhqD#OW1%an7ESfFLf;rw>V;IwjKP)<8dspR&(QABF6Tw{J61a)D=7mvQ{sVArZPgI+LMltckOl5YpI||LPrDFB?M9)ywesu8^FlCJYSz znhzOWiivywm8pPOG0TppFoG_jS7L}GCqmIITEqbSf`v?Ha(+6I5M_pwh!sdk6*I_m zP!u%w6&%iEkb=~pdY}14%_FrfSJ(BtP0-fO#R}d}vDS6pz8xP^OrM2v{}t0t-&7{< zO*O1cq7~-74ZSh+DO80HoXx1NGL~l=&Pr2^(Bz0Li%tk$c;G@YPV!;Y201l>n%h2e z#lXNI!_q~qm9?(MfGyo&PaWuBacvGL4SPU(jf;i`bIQOY}>lEjfV2kqgZ)Qd}BxmrG` zO95BFmQ)f?_z(H*HU!ko>gnR}u(&i#sWQo_xM87!^aD&p${@2(^B+n2@7?ZaWG1{_ zI(JWH=Fcyo=m@KKsIGr<$9OJj&h}m?;3b~iG~j_o+8pRlDS~+8eG6fyYg`&#BEB;Y zEG$mzuRKefV=|Mt5IC|{?^%AXE2(PtAEm1#2{JvvNnV+G>^x z79>N|xfw%WRbY^#_INGUAC#ljmrkdOzzEC>kLLQ@{^}U)85qI)Y;nX^!5ow66jjw2 z{PX;s#_Gzo5Kr+UgZlY$djJe3S}^E)zaFJaCz(v8K4x-mW5N4D(++xD24}zZzhO)n zK-RM<^PXy^nK)+g+wyl0l3E{6++lZ*fT#3)K5aa-jhs9}I`oEsgJWus<{|_yWYf=q zJ|G}ib$`Cqee*n;Ib28n!*HqH4NG0dH1IOpgjHLd@)<)^6nU6GZtseWdF`+}o=1^xbqbDuZy1=I;EnmyC6^@Xn-Z%eGzsG{(PHB5U;TR2;Fz zQb$L0qn7&Q<7u{)A#gQk+~%^moHl^BT!Z zDAQI)hxQNeK>$i9R6EL5{!wowjKmtXR_!T6hep5beE{-L%5}Lk^uiKfLIpAf+GZhf z2&3QMGC#?0;c$s&l+EOK$)=@};SNd)vQebuEI=O=Ld+>lW)bxy2v|L-57`s#=ZWCU z?7206>p@ViJejA}GFvr$e>_%~H8cx6Glj0Ltzjf%Mr=B0k(Yr>wPN#v;5CF zrWaQDOS_kn1SOkP{o(3>kE8__ZrcZ74LSn+nc&CZx5D(-wnwjG)k4b!W6#qXr~i?r zznPgC`OI{+W}U$HW+1E$U(`VtYedN=;m6VUo8U+JcUKDWpdFjinmNj@Ja&vMs(k=!)2lc|qD#$+ zR6RNC$JpIWw6CW(jqNovi=iD-+@N5rc(9xz>+o(CxgTzO`aR1Wyn1%bjfijB&~H0r zl!j>>_!pzUxUor{5lEH`w-6?&zg%V~LX4UW+63M#{g6b=$XlGvCHQ?_f3V*JYaHr& zzr2wz?4b>jO)xeVZlqJJta097g9hE7p8n(bBv43qQu}4Ds1z@QmU|1(ACls8!fVeC zPu=xl>ENrSiby`_xx#!(49`s%kF})sa}3ey6zmKXTBM{bScNMh7i28yg|d#6=sH~6 z+W%f;@qf5su-bk=7RlnL$Y^l6dS-A{n-Td8T;BaZEnu3aKG~i53Wz}Br zX4GO}32uow&(+~khleyf&|a4c){*s&T1)$mBAp-K3 zkwas^6f_xC^A4r2cj(=g6*9^8?N?n6$ryCCj35?6eN)giMwDL%^-j55`K9&97nZgBHjk} zV5W(lEVHW2+A(LO;VhcH@o=sat^FF@c+buS$cSKL; z)0rz%Z^sxgJ@bHpaH}6;;6aqh`nK^BF@7^z5!t+mObB{R{NTK(MIP)CrlH9V+;F8QLot0)OjSd!q-%cz@+o z?p(>dM9e{Gcv>|jVK&rHt?DF^GwDULxH~kA{0#1&stgS?>Ltdl%=mChjl?!gaeDXw zgc!RAekBTP-B^gExF5-QqXw_kSR`8-)2*9KMI08oicil^?>5!ddAb3w%bHffjY}Vg zE1!b|Rai4q3<4gHBc8!1s@b|eY=)2K0!_`XkL$2p0T)1Ejs0Upv3XORiD1jeI5ECs z)0USGuHomorZPK|H0H^PbdAc!*T0CJaA6n>^$=5F&uv4TR7Cd{WX?PMZ`AY6e>26p zguTO*WbRbb9B)^d_p|;FPdl%b(tYiV5|7}c`&9=VEch(Rq?0JD@RSDK92@p<#U&M% zwsJ@3vwwdqU!Y;-1LtGL8Fi4|ADSO{f@5JX%Sy^A3*(euoYDj){ET)S>KLdQv7bPDgC>Md`n(68=*G2u<2IG6nx0D4ZXUFpt3Y+nnwGdY%b!wo9vR(2oQrLv zwu6BxAJ2G%;Zt^WQ+W6wep0FS#_UKPNdW!pzG#O2!llOIBrH26fR7y-*26xnQ84a$ zP)41m(`m%ZY=4DHPj_lF<47ETz6zq|mitr2+HJ1x6pLbbz$qy13}40mw2Mq@BUf0+ z0k26mGl2XH+$mLxCh_onp1b6e!z+`5CZvEhfm}*gZ-{x-Isu1rN+*d;Zm%e1y(*jx zaniYnA>o)lwhRYHeG`pbL}^%ZB_%}7>920Ge@{n;G;ETNR0JoxmJG0(FMd@SYprf zONrm5n9pamCGR#VXnJoa5}9e4nmt59dUxaUPc&+fV&7@G`5n88Ym)^?#ZjUo<{|v% zk(T%sq1eA*L8xEP;jZG@b>A4swK5dT0a*UM5!g*zXRD`}QpHjtDpXd(=;B=1Pymo= zF<2OEh^xlM$pWoqJz90^nbS&T+xxj%8j1F?RQ75Ca<|P8yYqy<6Ynq1+FkN}ymy6F<@oe}ho03E}I!RPWjKD(gZ6j;Lthdr~eWiRiR$ps}JZ9mj?{LH58u}7cZ-eQq#q57gH)T z>=>$P6Hjsy<83j2on;-Wir6i1C~ank3xEzHEx#|cBT*Ez8oyFpQTx6_#9GSA%DTQ? z{`)t~nI&za=S%u(gTPS7^bq@HGwr^!~Zt4+-;1~L8=a3{)`Z<;Vxn+$jh z;J~W#6up(|wGNe!O(YIPH2zRk&p|fV=F-vX2M57TRC;p~*8>2IP`#AhiNVAEOulLq z2H{;otznA`L#~-oA!*ggdUt6Vm|jcKf$>`c0EIiai_iI&m#|hGD!7|E#T)Xi&oO6B zNHM~UZ^?;MOF&cx83<-u3WgvLR|z4Ed~<&yLNzQc%3nnlv(I@_Yu&b$CCE56QcMD$ zC?x5mgiNzt!ZZ=5X1-J2`|6Wn28iN7)g=(gi|kgsb}U^NZyEn{Yr$@Xy2Xo!1x?`z z>qZx$Lo@Z36~;{2l(?14nd$zeI`2VSrkRNTd7vUhk4cWC&XH-g0U43(t%{GJ6g#6r zX>+6DKuZ|KlZHOuJ8YwFyi3BICZ1g?hI*71ZC(?r;zSqHu3)^2^1<>pJvqV@+n0^- z$AL?ZGegd3$#7~Th%k0^5V$@PcxO>*w({JCXPKr!(<}`s`tgI@D)~!$X_<;ywn!zx zdVj20&)%^`ja2TBwnhTh{YKe}|HK&o@O(T~knFd3&N1e&5^7?5Dg{web4z#|Fg$ca)DB8&DvmxK}(rn5<5Da~&;T zD}v0WN?&`UgnnQ5`Gm3I!1*~!yEo{TzZwLj(9pOWTsy9$xU-^~xp-=8>ys(=dl&I* zcXu}uVbbMDpnMkwYh79Urx@5>0=VTIk60YRn%<680ZdaZ%&xso{O3VV0WE zFF^7%kU;lW`E9Dd04EEL7w4VUcu5= zX^#}(V5ddK6N1Kal8br4=rqei4g#{hU6X7##SlJ;>h1q)j6<36*FGAbMXbSye$*Ou~N&dD4=JWPf!3x&w?aCYX388H3C znkJx()v#=`JxvojEmXG41^&js**_4K7O88{w2v&PBL-qcGnSn z=|?=(wbhmW*|zX1N}HBI+>a%#9KMFUXlG_tA`#eR7)SC{LV z$|)qLy}-BN=cr)OK{&_mYVX%0kphM$2BAX@m&{)4ykbAs5$ADqr+gZExsauKTcO&Z+z5AaM)9U5 z_-~VdL((k@ncNgpHe1x@a6DQQ1-Dd6_8eX;ztMt!;$7$!tdLec%vG~fMn~mZCv4#EN<1e|T$@3;gl^x?I0o-}>Y6{N&N+gZDCrt%SHH66e7) zt&jKvz65y*qBZlF+7583t=o|lO`;Y_6bKU2oX|lUO3x9;wz0iNLTooPrRCx zj7G7a^f}a26O}v_YY}B5nwzh8Zxhply!}#;!g&n%91aNM^8)w%X>XrEl#^>ylb88k z`~7bRh)K8cvd3sWmL@zHT%YmWMD!zcr3JZX(#M9bZ`QSuk-}LCpSV`8*c%Llwr8Vb9KE*o@t3Y=Zio9svr#bz|hQPh&$qnGu z{F$;Gl2%Gi%i?c_LH(!Rg0`@hh1NNZu&|7vw_b=R;7QqhCwf#LRBwv zRYZ-@t$9$X_Cv?}Dij5+&FFW_8>UmXV@ ztB=$ID^(|jgzV|_Iv{_>`NzV4pzaFz-rLk2G2x%Mc{#B*3Tgi6ZZ9~@O`T6$9>Hnyi zaFt7-_Tf+T5Q;MWZ^L>I)j zG>jX3VkS75luJ>awzTun1bWspkV|eO@{S`(japwS(l8lqRH%|+#?=ha(DYA?;(7d+ z7I3s9aR!>E7?Xu#_H*}KYj482`}l~|i8cBJXkY{abHPxwAHo=jnc`X2Yu#|Wo);8871Q54mhT%TMVyI1UPZmu-AQ;IT++< zF(#%%n-a46c(tyC>pw{TW1!4Rxr*Y1_@%q^fAZ~G7ya?sSde zZ%0~`YZK01s$x)>RXy^4nR#M>?Pu`4Rf8FwW*^$D{+gF_)&AiZ-UR{|zD%ml{EGg8eEJ zkqk_SqJ1K0CS{z6QhJX`k)-|I+}!*$8|Z~={v|h>N=2+cBlMKpMcpH>UPH*11d;Z} zzF}=*dlYJBW(ve)zy97$*^am4-V%b#$%`#RUR0^oP&0xUI{}GfGCl7x)&a+N^IaD6=sxeWv#>wb*5YF%~So6WHy9qE~O4NJpI9=1vH{sfk9 z8FaaR%@<2vDAr4nq_j_3zZBuSJj-v)H<9wedNn|lW&ZR!BT0K<`=UtRX6IA*NdrzD zyAJVH=EQIzyqddW*17F_FP{{ln8%0g{|KIhn|RVyu@Dy*7t)^*SZ!AH0CGkU4K{ab z-wYrQYErZI*t3n>bq=^4#yrb+-BeXnhr$oxz|Up(`J-t0WWm^cny zt)R7FYHg;?Gr;$+8G^U5Ea`(sL9Ewq*XV0i|4L(xX@`;#;GbD!`yEX;Nmbxb7UX?q z!BOVe*`DC63L#z&GOL`EkQFKtP!jTUk1W<#B}&U)1by)>^c0V0sG_RTa`T6J0o;*s zDrbXCZEmL9nH-C3fQrJ#qj>98Rfr z36`P#sT`krg`rW?VITdiuy%>}{^o6_(6CzkbmpMMvGXr$EJm&Odz>gd!Bf(a>#sqY0+JvS! zlxU(@Iov-6FujApr3BA49)}%N*+EuWy3Y;#C%goC#&Fw@LCj-8!3xMJ(qecTM$)o z>DX(|03T4ys2`l>bk~swTV^pLa^zdsZ7Pz1-#?ay9r}tEZE0Z^JDXu5maX zeOlI7nj5<+WdgG1R(|8U=W1lbKqeQuNttZt*m2<0CKA3VUuLxw8}zPa3O|`9ME2_b zt!P#evCe=1le^YiNe?o%MrZdY-_{b?Z6iC^NwSnL3rFE5x>=y|EO*}HId_z|#|vu`4_S z8RTRUD-DR z0tDLul525)GG(@KV6?ZSB;L`cKv`#q55l0kU`4%}`*8CohI3R$@m9K8Oz^R5Emj!C6m8j@IkDR)QAIfj= z0@g{&B6^w(tlmpr4jL+Y7f*wuXUGD+qFA{I`oJViYm&NUt(A4$`~)sR&%mhWO}%2r^TCLJHpvAiO6o>^iM>~3mI^0#vqfJVP~#oh~G zU$RHWStGKidVVr-!TUeS1oN&+CF!eXEaCiTb~~34OG^`~7lxFF#Ywary#f@Sfv)np z&;$(Y4v~b1cXBLPTngC$C?eBD>S=M;OC$jqo@Pn(Snkh0G5}fgd+GysD2h6+7YU|< zWFmV0vAB8N@MV4&AmKVWy;55Tmig~v71ydlGru~uUy7#4(n3-)H?6GLguGVVq-%Y% z-O;jpqc-OvPjp4n537ABZ9BrQZ)8-2d2F_(uFfCZ;tEZPQ$^!sL`T17z^Q{K|EioV zh^f$*@pLTMUKOAUX0*d{Mg3Ol5m!%@gbF|uvc>MKWKH1SrbpgaUHAy?3EQT`k{jI{ zj=?-TzQFwz>IoruNHb)NFLaK=Tjch;r9VC$NDO+7S6+GL+WTUcjmFo8DA~2QweOcdzsi~_AxX|4}A@T#ZpdN!O z_z7B>hk=sI_2DmH$P)Z=l^RYguVA{EI1}${F-_Ay1Ndmz%Rin46Xn zFt8I+Hp@zj71bEGGy`$B-De}CUF}T>8Yh_|!_D`xb}G|T-pvXRgGgh$TNS*A;LpW? zV+noje7~)g{6+BS{vNK(Cat9#9_x>L^LA$$3PbIx-P+Q^k4K{-Yj^)C0cO|X`-r#Y zTgLqk1a>@z-)sv`gViK<)m@dQ>}WMqDqu7&~QYD zQH_{%Sh2Y|Lk1r}Fn&*((r@D>1%|;=FzjZuryE(&F-MehBBieRJZ}PfkY2m8@LrsR zZOo|08O5WN6{sa|>jlo$lfoJHpuIU$Co|r)K$(`Wtkism8?js1Pyqv=)r-T)___q6 z3xU-hE7?@EFy4fy86>Eteak61b&dqlEOzLj3n1Yv9mfwUR$*|0jMc&UmJ%9wLGvlj zRyi4}jXuD>;|DXHxTY`Q6XAA z^XNQ=c)w28ZZDuASGZ1+aVSV|k*3id@KTTS@abM2UF}E**`G?QS>eIU%j??qOW>`-QM|GH`a}>Q_{c)jrQIlS z)Z&W+UZp{M%y8r_f^&PEkI|#n9o=n`#|E$jlQ(E=w6S2(XrxznjOnIs)rTGrziz8= zwS&6NE?Je?XPdxjz*NpzX7Rw;n{=Srv|Fh;5(&{D{adtFTpUlpj5q<@kDqW~5Levhlb zclmGVMy3X=-~B&HVD)Ceckf5~cXKac>2Y9Zz{^XYQy=4B`&EYAKT@Byw zl3!9;;fayQ=~QlEfl-2k(O=|~(lRJIE#W0~O(Vf@);i;44+1@YCo8qOt+3|rls@kw zv~l7Y!sEh0W_X)3z*wPGjDEXgPnoA7KE35p z^}SPX8-3A!X_^02mX0+pajM9>48?zXWY@j*TyS9DBI8KI+)5>%t(+d;!jgA(re4jG zg%=j^^}I7#7}%Pk$qFOwcMtSbWsmd1@FbcLOFU1GT8}_Q5r>jJr0_0Z@|~6C@zoRU1z70}A~__jK;IR8$xKBw z_iyrZc{;ybsinz>prfxMGDnMe}GxW3KaPr`;WR$1RsEJT>I&7Ex z>3-gZ#G6lnA~OdY%0R&SkGW0*EEhqvrC;W0`!!Vvep_CsZy*|{WML>0K?CXfKQZZC%#34o?BlBuKH|w ziwt-K1ZxIecP>@grBNECL<#dB#0e8sMRfbux_1g1E5Q<+@PN6Q_78|;5esU~jcH}A z=RjHZ|I-3g-aV`L7L(NJTGH2Sla8_XR+?yOBmX!~4XHr-Y)GxuvOggp>QV42YXejZ z3}749rmJTIZu%i-1$|P(of>#0>tBJCs%8irRw@jZn-Bv=c;WFf2*0d?z|K=1kUm*i z$JoouQipHTt;Xe;RYoZRZr*>kTMFu(4BDggj*P`YIZev+YmZPdOhFX#Tq3r^0I0EH zQNSdLLY~)5VLERa>Bnr6F_8~a70t)R!>rsP#I6Q`PwS$kr^mnT=t1T)WguP_*v=-X zXOLyaE9?DlGs{-DzhVG}v@pZUAYrlVdE2J~vAOq}UG0?CnvQ+cNp4LH0uxYn(Ukvb zhNCq*Y|V*epsX6EJyi59R~ck0CtVM2o}lWxF3H^hTom~^_5yX?QEQ|b z2gMsomk@62vh^Gzg+Cu2u~XajO|a2GCR>^$$y`yyFt8un=OB)g4)T(BwQdJI)enEI z_g(V+0vFK-tYXOp)`g516QfgPNfH?Ty}n4YjfnUIuC1AVfrzd;zxFC_QF- zZHq*3+@88VV2r8#Pu|1Is&dOpQC<_fiP)Jb?m)+2+L(JYFFR8dJA=#%cm+;O=Uqf` zlHvaZa*Nx$yFY6k{A7(=D*>S-r;KN(p;>txFgY1DadBGV_ zA=9DS3dtm~AE^;ec2FbeD}-XpBus&@2UuU?^?@YVtY%lMV6uL=R6zBr2cQ@qNrOwn zEso6ZMk;WI(3;P?;t>!`(@kGr6Uw11J6*l9(n?B7vRY^=hmF+(spq7;Z*M?xdFSI; zvjYD4pWTii4-a14_uim~&!-;>)L@96mdZ@7w65d>6P5-9Xkxj==rlZ1o zfGSa?<^jlVto(7jfk^05VH#GwhPj?Kf27k&$(Rx6sh(wXR=lPxAiKWf!8K%(+TrBCAeOI)do{&9onVN?(Gnp$yT|0%1+TZN+3BmFFy|F$s9x5nl9 z-?aQax;m>4sl{+rsLmx>2(_kUETk_i6iIEOmoyp4kX^r!KTYy`Ia66~mIQ?BAllut z+(=X%2gSnr+(k+|D38dV3MN_Yoq$}+X>A3)i zr*BCwyPQSI{Q7P5L#r0#`w}(eGzw8807TIW8Vk*1h~&xIeB&%#BTnC``YC^ZqF%oN zMZUw!wI(3RM^j3>P@?QI!R)8rk}Fl@z^Qz9A)}I^C5RQ7^n4*G+LKlPZ>V0j`P9Rkb%NS%&JHqpZ&8Bm?VRm!IobW|q$JE4 zEeqe``aQ8QeOI}r0Lglhc44m}*~qiy6=qZ5eT#;v`);LGI;;kr>IIFxm?YjQQ~MXY zbUHytTAMXWS=pd$K&P`6)jv5ZVTl>4icYcg?7@l{nm1)LjvP=z*?=VDs|f13OLL%I zb|!Ui>gM(cY`%CH?Cw@P9U7OHQ!VEm1lMWD(w8KAK3%jf)K?2z+puvqGkQxIT0LK2 z`Sb(YR?qT7Lr!z7TN6MP&bi=nt>|L0D!%{!HDbb=e!)c=JJXo z@ylG~qM}gMz2xiprWokwvS#U$ zM*=K72*2dQFKDZ)cNKme053-Rf4p-?at`6T7Y($KTmmt?ReXsbUd7U03RrHn)M@-D zGY;hPUDDFhPGJcHKAaqwL{61l2)v<2qY`!@w^9%h%d-{#INUXrFxU?=eac-q5YDXy zRBjZg6Z6eJgq`FEe60o?ROf$QS_t~TAm`Eryp;#YBxHavje}Ol=cq4Oa1}xl8&zBi}&tyxat{m(aB^`R-XLi1>b_D!? zT-;}}TJ#&t+~t5UweM%)cQeEPDYGC}1bF(5(dJ^&RKNx}M2^JqMaQo5>c+@mf$+)Visj+RK zYlKe&A&%yt#_Ba9dS74d;n=YYxX<26nb?+wgGi<)$t*L0zv{Df!tk=}EB!}Bluz2@@rExAtWpL!Kx52?0-Gw&HO&2JtvdY1nF(hd2 z7SyL@EDo(%3GHfC)aCd>6~BJ~M+jbUTmr&10m|xhwr2_gV!%*cqbt<7MR(EIyfMZ* z?fh%GO#iTu8SE!X%F9FtS@;d^Ab;>!K~()N4Jm5rT1^T;A{@VZ&}gue6mjAS3);SQ zMd&>~!vJxW9R?|~e3CvKmtZm%fa{#0?c{nV;P1tCT}=)-k_df{VMf$}qm9kMLaA(s zu!EIV=_;?Dz5$FSjxCSgRq0XKhDR*Z9pzUf0?oqB>9!MI17y3JJ(h&bcm&a1B`Mo_ z>xJi|PA%w(I#QUCdhQSdC8Bh>)M|-nBuL51YUaxFj5fc@DA?Js4-x1>C@Uui$6?_* zYw`C4plrN>jHw0(TCZkSW?bfXbnGiSe|P~-CG74}W#R4b(XSCaB%bkTDvb_YzlinT z?r!4C-2}BkiE0x3fsJ8e8+3{7|ssbOZ{UI1ImD{@zV2 zxsmQcwiuVCYxb~a?bLJ9XB!#$6l|2mnL|Yfx2?;SJr1IP*z8f$1;=5<5hpA<2F9y@mnS6_8R17f zQs;M{0JO*V5b53WvAN)2cIXfyjmyG4$VE{;zRoq3kRWGV`{W|E&9Y|)-BQGTsuk>cLq;T9Q4wh(=- za{}W(`t5%VnK^}5$PV~(NL%qpo(d{R60-Uj7A`Irx9uG`6Gy z1!V;#Ono88;pQT^1|;y~N=I{_;0))$DtyBV2-ZJlbxiiyi|*ri8jiBvfdkncX`#oR zdGx~9WN!GYS-II!$x5e)6+k?8-Tc^GHhQs;FeeqUptlN|WZ3CG?OXi9Tp^H_wohy_Y$ZiRq5;rWOQ=VEhC7s}xGm@Ddpv$b~1}-E|(io@N zEQ%>N})KKO7h1 zGOPk7f-j+NwQp-S8l@9(%#Cmg&Eg>yK~dSOfJZ;H4i&j=rnJE`AV*$uiay*QiYz7y zSMRj{L#BP#+*&T`a5`9Zy#p4RO-Py&+qRw=z>eo1uzxa zPzWifpA4;qE=6gz#2bAtj7Cyri393t(?T(%kRqOJY6=;?H)O1Y%7end`D^TyPoAjb zKAbcQ%f^+#c_JB#_4HT@cGN0NGg*BdO1xnQ z+!IJhu}E|S6K0}vT16>l$z>k}J`dEiI@BL@VY>B9ZM?%8>kJMHC$zog2l<5#5_PtDpS9g{2tZZt?;=!E^9A zMq%8>C_~;m&zK`+jY3$vr56Kte>72$UX9v0Fp3HMAC?>kW^Xq>9 z_NRGMUnEilG)oLown9&!3&wF1ch&Kgf>J3;h3uIK`z z*d=nb2neg3n1iExdo%m{`z^GyL}`s@N&zRw#}dW!rYxeQ(t;7yP10}Dw6Gm1;?9k^ zr4EwYoDY3AiZTAZVnmD8OeUDecJWUqa#dYpUo;?0khe0Qx(!5Vp1*Wxkzvxz^{PF+ zhi7wHXCwE!G=4uswjaewX0xFIXC~%H1#9tzcknN1NO3w4nZk-aE;97E2cNfx+We1< zk(_nlwR<{O=I`IbFlEq$*oo5k4PKgHGwX^Z53$14!Ba=3U~M9L-3K4PC`SD}busl6 z1qB05+X7}fCy)i(f7kZ>UUwy1;A*Ec46N2yH^tFI+|a|CfW zHqo?RG+WNa4_Qgp@&}5rqEf?;l8x!pETGq_m>fkQldDy78hp&gI6YOBiQ*cb+FhxT zk3$NYsValo(xM5eQDjwcoa{2AHT6QWL(acpI)>_nf*xLOwFZ8X zi-rY8GbNDgoo0V|vrA&CramC0cu>DW#YVqpNuac}LBTCuu!S^oS=ri^QJibxgKj{H z;y;0oAVs1rz-C<#V}7ZdO)z&`(Zqm10wFe{f?kac9X&lg&3qA_$v9AZO?<}K_Knib zOiWJUObk4irwF<3>C|(59Z0dkAwax*a_FAm=c1r=yv+=EvH&mBndIur2P&PYUK*yH%|RBhP-PmcdF^Ygo+4t|`6I?}gee2UF%%Fs zDuCdZ!Qp9ejsS2m;S;6m*Upqb#X&M0_gKPjrDX={>HL67ZeX4RX zm2t92{P}(>+rC{~r$e;_mt}^TFZs0;DHowQVzD@|AB(3lN0CLHkYMwA00tE82%0_1 zpOSk@uenBHosI_G}0j5^;NS)A(11?8znSyo1gFR zF8~>37Q9%cMr@Th)7t1k%{h*)8BznlP76y48T5!oUhQD^@nvRX(Q&DwW*^gpiK3|h z38RDmDb~I9>H0a*MC{YC3;i}2u2m}gNkFg+wRVaxzd|CK1R-}g&QmyH*B{~YyVA+4 z$OJXmb}BqkShX{)59l$cY2;8<^Pb~YE4nF0 zo3*Ohr7paWO4A{`zf3n3jeEHTMfIVIncboZ+FDyXySrr}pOhUO01X$2pixal!3^@W z6(laK+1a`&dMr4ZpT&OGDkgj~cVvAJ4t-{MHst+eBd+IdJ}H z1JoytL49LTP&gX7F@FZik;I5w$Vv|w;o&z#RjRG#)~#FCBVH|aCSGWH7dUR3OS z4+0~P(w7#J#jGc*DRxAY#EMng8<+WPuq)58#}gbADm*NXeSCTcn(Zg1Y_WXEcSf$N zIr?J?a&j9k^eW4oD3*vS6p{3XA3;G0d=E7tCY-!YaGb|oAE}(Y{J<`%O5fOc=O!Je1glvxTN!&BB4FtW zzGRBPs-7YTaza0?M{EtS5l5P{#fbWzB$XuB%){nEc*C#@hfAoeka6~n0pNv3tjB)r z?8t#ox++K79A&~x(u+!zGNv?Ad!~&M#iWZ;#eis!g*4x<9W$mcJCwK5N=BNfcFG@B&3pfB^+eU-RkZohExk%`87xCcAR z2BlPfa#P3wA_g$gZenDaX@m({6VkD-FXAnxD5os8Y&-9h`D4;H!0asJf}x#sidRj` zXrWKc=sj%+C@v>e9yA zE{5?6`)jQsA4la5MlO?AJ{T5`p{@vjoO|o7B1Mceh9FaU7H|o&)$ua&kiOE<^)O_xyBi*bB0`+Mm=gAeP z7eR(=^}{Pgg8F!vP2sr`G`^V}x5ehr^4*b#8H&W@Am_-r()sqq{Pcu-{z6sL@$2pRWe zDRKKth+q}El{NY=wDK{bvw8wb0LjxVbC%U+G=p)2X?R!U+O;#!45z2)7H+U>*E9$V z05A^Yjtf-eWr^0YOE=+K-?HbGB>4nnX*ID{kNtJO1pY^nhx82$Qj#Lfr7t4aVN3%2 z9;8y$1uc*I*bbN;DK2rPzbib>7RWiLPtr8vB}91;R5-56d>Kk?_s1K9CzxmM*yQg1 zA5G`rQ0W(F?QGk&J=wNxpKRO4$+k6_lbdYU)MRVoR8xKDckg%qiT%EN?X{kV%oR&6 zIpJJ?P$V4vh8%Cwu3dmwfP8F9-FPICOjnTk%%dc+$WiBiQ*Ye6x6_=dgt)n+38`l= zcWC7H=4Kg$p&a+qc;^<2wU@wG8|{-~hO<704U46d{6jWJ#tapWMtg8 z7K~(*O=&gl<_iG~o2JoSs;dAToA_$;NBVQpgDW7D9?B1iy3r9pc4U*fAlN}ATlQ1j z&G(KDn8;!guy}_byZel%<}anGper5>;6O-Y>#=T9lUI0_D?Y;VkJY3KLfknACM&CL zH6o3jE6rg0E*o6-;_@ccWn*I_f+zD+(wnaJ1HnC+)``OWOdEBJS^{)!snMc}EWGHZ zpA&|do}WfS4cs4VbyD64zMKS2Mqem8idWe*7OY*VjEj6xK)9CMq&0PSvtezUVT_TX zzuz^GMn@4ZR{4YB;%rJ)$&oZ)Trn;w637!k{*e%xBA81~mrTVe&7i$!ZGF+{{99Vw zw3U9>M@@pd!70#vMEdwAi1LP$I07O74}E_)osZ8lu+|ow#A$VrNh>LQxsbGPiYyt? z4n`RG=>g`cZ0&n~i{&qag@qq^s0CtXqC=>}9%_wwrOhMIT%Q-bCi9kA291SMo-Z8y zUAhs|daF2ZK3M1E-CSatMoi_{*ps7!WK81YtLt6ms@xp7hoe#N05n^8!>OpNX=MG* z^4_>;LQ?P#sgSFgs!IJ4SyAFsy+O*c-q z@93Zp7AYVo@~PFm1UO5O#8U`u-85 zy%tqaP@u(x0|w@nwH@-4k`YSn{w#ISC_Wa<#+n~=o@Txq^2=iH-xyN!td&ZW)nO%9 zIQ_X)rGk{99W#8+$BAe4|J{rZ{ctpi0^3cu$vS+YL+lP8I@EoLD{b&cd6^)H#mI+liupDPNoUY$^y zGE2%QuR4b4>sWS=cnTG!4+r_V#!Xc!jlaT&(PtgNNG4K*A+Te>;;8ZviA!h5}MmoClet#ih!RgwT2S z7h;=MZyW_BAoq9Mu5IWnPwG1J>G|AeAyy5Jdu`Zi@-!5Ut)ul+-p#d+L4Xo+V(8}=$pYz zchP;$Hw`iRb|s&Mopq-J-x~ja%uLH_aB+-)?y)MVJqwG&T|c3j=1palYEhy@eIrDf zlrX5%Xwaz@gApd}P?DrLxN5S*)Eba-^?zBwX}$-M?N(vkpMkUi8)9!2cS2I*mvn^ndZsQJfut& zqvtGpRQPxT3ha5!nai7mfRnJ3EE|M+3%GZVzY8wNtLUK<^6b`;2A#;s&TypCx zEt(7kg)#|=Rx19XpObI7+`xQ}TuLA!`5z+0!ud4Z%qYV*?kljN&jIel~7bmhOeeRi_j*3qiyuPo4oX`hxlFY#molH6YN`TzGFr#eu{?f}PjEY^N<5CbQ(%Xpi zNVfBKYhq@VsAIGs%XUb+40h}QjDS~3Cz(wVAR0V!v(^5DtB9qweH*Tg>Ke9A7JD@u zogwVXfwG-w#4|-lQD9^5u8+u2z4&^P4M9D0a{+JBY=t2sniSLu?CHs++6M_RK;EH5 z#er{70R+mtRmw0OgG<#*LF`R7#?ds6ma%sx`e6itARjM*bY*c- z+E`I~yWLqykGg9!%nV?yaqamr>F;Y~*OgPohbC(@8A7Up*8F!o3XV!TvV^K7cJTnn z>h(mwtO2C1zjx$tiG$}-wIW%xsRU|m$#~JCkDD;3QFpHkcJ0s4-ULr;?Ro15R4YEo z&qAnmKJsSaT+FWGCu&%9*snonTQPp$>tz`05Z9dz1FxTS%9FA7gWlJ68XA~+t(9tKH1}ABk0SQEh(s9z-d%~bN}AN-&MySUg^%4= zJo}>76?ckvY+((*@3huqo!ANPoRlL)+sl*M zw`cfG{R?&|{}yW2KX06ad=9s;X`3WY$m6IfM=gF*eOJ4IDKzjSrq0hv`iDXfMZ{U7 zo<3SlTc0v)=STOA3lG)n=C&)UCm^Wd=ZY-=Zuxp~h#cvFW}>=>5z(z{0gIG~_<%^~ z`{H~<1A53V|Hf_4T7^x~kAR00)UTW1-oSUSTJ_wjebbpPELut>j>&A6Y!AMgkJ5|j9*uOlrr|;3Id)&mM ziy+fj$BWvgz5NRqifN<4KELTQ*h68wct63Te1>U_SDx%&BzeV<1n^r+xJ{S5S-&a` zcUR*PJ1F9^73W6^@RB z>0uwo*vUu%K~NSYO_ zTHl!D-j1(K%D#8U)fgC}CG@%#m{b|rnV+PWiAT4=cbOmZt_V{Nxl&+?$I!w^;23p z^$1HdQ)<1!c%DJZW~1a9$;ik6S>0;p#1TFg_Z^AS3=FF4v#~;B9%nmu{S+>=5Tv!J zak%3VN+Wyof)toboa3+qg3RDm;1@r4O-JzyuXH?&>`wnHI?A0UH>5cIFnhp;DuH*{I%nhg|$HV&1r_UAtef=TCK2deLd{_ z0)UExo>pRlGhNKMo50|=nF~3SN|Z+`npx2ru{17dj`GKpYMyi?- z!7)Av5AMQngRXmJwY_mm=c>97jDs_cA{^OCf7scqLGU>Qjq48T{cp377TpA8++66 zTZzvT6bgTPs_MBa>{ot#JXcY1C~ae^Zl)t4$~J?l1mf< zsbgKIt8x(a4UG$mi$10Qkf!ZomA*5ZO|)`H%#|DFOmgXnmPEz8Ec$?%_c1lW6w01+ zGp&ocB21i%-o|?XMIY;d+Yae-?%<7ze^Oe0L9*cl!CnuRuX}7WOkmlNc_WufBk6{c zKKTjxQN$X8bZlRI4O@M+?zyQ&Nvoweg&}~&Eq?_v+XS{YrEbp20Nu2nrRpn z;Jk%u%RFLmcj3s8z@Ml=Xh@JjoR%A?W$aLpEyyD+&|4|Y^WnT5fLd#t~}B%G&A88bXNotVDd)@}o;Vj3YPEUNj&Gj@3& z*~+~H3Q+v2FV0-BZOW5i^=cU_d)QNl4l^e}9zeGtn;$zVr>9c}1_X0k2ltCyl~&Ng zVNTaxputk}p$j!;S;)|u6DLg_eYf7gYN)opzJ44tO)c4g6ejyw$K)F^ww*DVP&Oer z``HSbD2`i$!AmFAxB%z~ezx)W zec35&9>%i!MzmPmJ7Z1WMvH31phAtfka=?u6#>bl7hS@IVLvg`k?p^9FG1f?Brj}; zQj$UGdkHQrsbASTY##)qckBM0VZm$V=rmC~?HKe4nEA_HChCq?J9>*pwv+DNHp6#C zmq3}0XNvCj{ioMb3#3$Y4?~K-Vkr5he@mAOF$&Hj{yPp#!oLg8Eb!cgG${t+Jk8Pg zJ5^J&jOpoxSzI;Z6uIbAuJqi0Smnop>&G|CrSlBA+H?4~vxlhynLKLs@Td9 zz4yFV5NYB(Vv|dlpI^46OGNN~XUkn#GI;B0!(U&yd} z&zgh3F$lYq+2*T>~sdsyIlG8 zO6f>vQK^pVn-^r8rnci7ilUxwJ)3fckq%Ea)yL0Pz-Z;U5}#8tZ!7`~?DP=B>s6~G zMF8oh%p4L@v~%p5u?w0@inL2J;gDztJhT8w3t3Ki%*VfJD*x8Mu7j5yJiv>&9T*iJ zGTJ=}aw3mcZ^V;*y>o-`X7wLMe;5aI5zd>B+n2}fuJgLj{jp1sndqv{us6SK@Cp#| z?h4Z)Q7K&3JlmWWvEXic<>E+Mx2N5uJCBi9k;1Umqu@cdkxG$}E|MTLm2wps_l*ywCSXQIZQ+cBG|b!u*zn>h0Jz@seKSpk2u(rdOvmYts4~iUbmGmM z8yZLA+@@`iWJ$>1i+4*0rh90FE03Aw+gU$Y8K{qlKyi*Uz1E#NA7(q`&{$w}BCE%? zwHrHMBr?z**tuBkiZDs_&L5942>RXMNMre>PB6j@Mw6C0y`+;$c=CSZ!vaFdBg?$N!N8QF%mi^C5VPhE}N7${Zd3SdFIU?SOAZ*9x8hXRK!nmM5vo@&ThEE_|A|J|>@qfLW{KO`?GFev<2| zZIJD@?_^BJcQ5xRkvW@*aAgcG6QDddD^pv)VQy&m=5yCfVIruE9+OqiS52QHj~kM0 z+|o4F!{>O#p%$1fNyUsc?-`0ZMYS<(Xd`#fzC)K?Utn;$J2=FZqfBF=+|jFuT-2R# z&ek<e&kh?Z4ad_=drICJXeP?SKz+IXby9bujmH?XFGjAA**7{l zZT#8 zR7;kQn4~Otjl@$9K?7^9I5p<@|Dib#?5TI zzQe0MN-BgPsyLufD{AhS+o*oTf-iK%Z~&gf5Qk>d?fs(MC@RxVUVu?QDa4PvS7=9J zRg#wvA9;m>`h^GOB{S4cg4$8@<8%nejNGG957+EP={ zl1vZ@Ela31#b&5`Cg6qLJ^R`1I2o^7YK|;v12Vl%s`B#kE&zx)4taQP7IiYSw4Hx- zvEz~arw32`wkwJe;vlo6HSqxU9X2o7eP>C2e_Z5~UB2qfn@VC3QOSu^KIS|vF%cQ2 z0h}iv!i3lc&u)q;+g(}bBOsAb64a_{%^Pp%?Ce)f9fau zjvo}OEBP!^EK?T@qEk}>am495E54gE_{lP@(grXvxS-bAcHwDo8!A((XNAVMzl>A7 zIyyRl7w|8=BdCPZ+PSU?V$6}Rnn#BSSxZfE5O;)Hi zisY2NPw`0ADl$DZHgWxKEKL56AWUu`h;EU3vwHbto3Z=DKWmvyoY0u(55q;!tS=#_ zgg6F%07l1mfdWuZ$f(x~x!Xwy$giYy`r?;wTJqG|(h}xEn6JW5>cn}nQeXPpszC7W zM#Sh@yHnIt>tFhEEv*RJX9&`eO1Zn--ObfiABa$!u!+M~?y)qdTBcL?Z5BvIfWnr- zDlZ;)RP3fY-vloefC=$DNBk@Ys_5UQv}J9rvm4m~x|J;=B#8tt;x$V(VsQ5?y5+GV(0=FKI zP^?}ftz2@Op$i>fZDts45eKvFf0ow_BS2+Ax%S%bXJAqHg_D%Fts z*nCrXr*y{}YEA45&h@U1N`*x}EV55Ut|Z#rsq&!sdd^CqRPLPBV~FcOKhOjb#~1&j zGHD1a?`U{YCFu@$Pn;}AAo%vU{5Z%3O+}6JQ${r%?3xlRu^SUlrK~PX?aNa%epZ%< zh#m9EahdWLoXu7Zak9qw!I0c3`o*heBdg=6ORRqYexG8E8nnLxD=ef8I@ONM%4BTq z?t}F&^09Df?dfaLY$s7%(2aRD0yx~TeG#hB_OKF8C#WTjLAg(MeC@S^A9YTGEF>H$z|(4wtMCk$Uh%H&M~S~ zH6i#tBTeDO^bcu^V1}9LGA&;663n_T0bn=<08Xvo5aM5CjkL#|vO+G9BRmjzYK^s= zRryW0XKKraL;cBvOL%K%r@S`>)Bj_nZhAUiK>_hmAY^T;K2$CONAm7%0-UDR!reVh z+1S{adb(Z9nN8S5kOw$p;6~Wa|FYKBWe*pqj6;Zg1%ld~RqO_Tef;MN3O?g_#eRJ9 zYTCYPoBXr;t8bmul~zklr&3-$`ZbU9aVl&**RRK$}b4xn-S@wdF7AeW1K`4<$&YDjR z<5RpjJpsVh*itZafw7inXzjEd?EO8^w{TW_n&g>J6wJviih_`(mM6Pp&^hjD=Bcrr zK!EV5A1GS<8_=3IKhL$!Ej+M(;i|o6LsxI_Pa1GH8`h5;n=s$LTuBdJ+=PmIyF8$G=Q&M9c+z24F<8oc&Z;WY{`MO0dNZP7 zj$5i%8z~>N7skEX>E| z9$UW499tsfQoeL1UU4#OI4+UgiJwK(Wc7^QN&u6!`a#jxzthQ#w?E0jiVE~;s!9lw z*%7(r@{HcZ-e!QD!VA)Xb5c;ZlO^A%0^0x7)FwE1K!oV}`Wm?s^Y@EfoSaq7fs3+*UQlCYs1&0N$^*+2xt{k*G;8Bhn5gK5(v@`lbOwRTl3fkY)-}k;1`AHMWGF( z1|>0kr9wO8oEf=QLl(+CdH@wO!^vYmCkV|pzGYVv9DVqr*dqMZ|NjSKCX_oWGh=A z9uG&bQ#p!8OMf1O7;0ot5|De1z>W+3GHS?y(mLxR7&b1zCAfrDXwhQ{PvU;Aq7d>w zKe2x!4i7m8wO0Qvr+6Q$zWl~d5FWb zvis2K=GcHMjm-Z#i_bd|roko=)&}@Ad+}yb!Vl08VR6*z82Iyg3S8xR#Af;Y6+Hz>i^j0!=T^n~oNM zTBCni>TIPE;&46t2vi|6O+$u9CBF=gCPTAe0Ex6k%jFE=ptim<9z2Bgb_kj1CtOYA=5zsn!FNdb&Dsp^b5;%(R6yyId3nh|XmaCo5Ev zk>{eL(Mr;@hS~-GFe0^)#$7lY>x@#?ilniz=I`eeuD)c4(J~Cg@2{(-eoOKK?k5S@ zC)KnAAPQ%<#LU#qgSXm-j`I^uuQ>Cny59p{*ZN#q>hUF46!3bM(~f4OQVN7l*-VsCPsMc-fZ1|t=r+Acqf0X` z2DD?}p#Fc1uXSygrW;azmH=OG-w;$Z1 z?5gHriu7gQL&Q%XS|J|l2l7s(@F5uZeB~Ii+VzhmiNjSdHo$|Te~Q_F>veP}w*%C{ za>UN3jmm!`2nt$Dl4dX1g;p>uxxzD8?VWMt3&<}v5Xb5P#mU-Krjz9T9IFo-n;5<+ ztb(%$v!dffv7wfEWO~fLKDAO^JOBQh;Esv}lIQp?lB6}czuhwisNW1w(&Zx&J1am%4w(Kp( zl=c>Ht-+j&rt%F~--B+OP6Aro5j4w)e9)ulP80mC6ZsH+=|ILa;#SZ#Pi=~e#WnW3 zu}oC}Vs1oJJUHiZ$OoVRpyUMI_FxW{W;U!{%!LQin$4CuHr+P*{Y~JB;cJw0d!tE% z@csr6q&Nq^Z;RoXbS?1ZDxuf!<9Z;-AJtl>^nDP8niEJ_rK|zbs(zHQ7f%gH^r+%_HuNM6(a;QV3fFhkDdOo|=gr0VnWxYV`h&WK-GcjqMj1 zrnFGhU<6U4o5TKazEVeL=Xs*+K8rW5DwvAf$-}@ud8Qu>{qH-spJy_+vQatlSca$q zwvFCo%wn3eb1dtkcYGynflKl)X^*#{m^L4j)=?Q$hwQ@g%FI*PwMq_e@1#j~(YJQp;f;c_ zEQqdOAULTv;YNx#*|L~JmBKB!gvJd|gr#RCmkzVcmMFI%z@3~xB5|b;)8uCi$r6Xx zRJj*gMi)<=dex0wZm7}hHi~rMrUY$==~lSO?>cK;=E$YD%6`Hydq`%jEbk<1AX7#o z_MJZ4zOn_m1QneMmo}}!gVz20z#+iEl4ga_Gp&~dx51D)&B+DM##)-ih03$0)NoSY60>Z?Uiz!>_hWgmO@msADZm(I@g)EGu71m4hNoshV5Voo;=%4j`l#|(le z>BE}>|I@j`|5a?At+4O7EH{&0Gx~AEoo6YZyKE}`)zHxRjEYKqJP03p z{q8;aIne3)UV?af4lVZtd=cAHP!mA(t68$v7GeFp&y3NuYQ9Z?}eKs3C z+yCm4?Lsn@sFMNy9Q+pP+dhFbO~Rd$T-v+1m2@jam>^fU$8R;N zQ=g#}CpOvwI?T`@6F3iKFv(yjEWDhjdz61+7j^)$%ntbexo)CkTWHFD0#>h+Of*wVf>6x z8YrnyvFQ-Un3p++?Z#|nV_P!Df(vs(feT9p8T@y00=f?mJ_Y|T>a)3V2kIiGFfN(Z zX3V9(*$g#dqIBBK&5(=3iFW7eA@YX93PJu;JF^biEOFF!7s@NWl<1VA518D6uT(E? z57m#d5(*Zdd5JtKC1E0zs6-y$>7$yt6f5kzB<3gd{0wRxJ$6^gnGLo0J}7AY8tF6; zVk0Ks5(fMj_-{pxEx~2(uK{Mx7ZEgUw*!&YlEl7ME0qkAEl-X)Q3Tj96J>(vH>?;W zd@+R>7|Xg70#a}mcn1(cbc2y9;LN}Sx8(%1|9t!Sj6}qx`WyK=&o&?hS{?^mU8F=O z4W3xF^BCH-KJwe#ROQcm2~)xtr7ENgFLCYYPpZRCO>Sv~-% zJ}rm--L%r`r}|<72Y8{2kZE!E{DGw+(2hWnRV08fvDcv2|Bxz4cHRo+7BXp$jSu_B zd%C20m6}NFuvItWwTJn&!)<*-!*!ZhwsIMl>qR>im+XBnHz^WUTeYAIX-eS1YhAq1 z&!b+N5Rz(F*{ZaPF{g%o+O(RGWFL%WL3dlRJco*zbar{*AQ$HLnb7my&)!=e9lv$h z_vvTKXtlj(%zL#D<1EYB-RgOC(o9yIMB1_&{JY_FxL@{5;>BTn5AGz+N!3Td_f@}g zu5};1akH+4>#%gJ4e(E4zMGDSEvtCAy+RyB+|Kcwka?@)@ItW!bYNnrNt36aBYo0d z9~VGzx*4#rB8X&k#rkFwx@+z=2-$(-GtYTz6g(=vI$bdGnNpuET_@3jtdYodsnC#F z{=2FuXkU+`E^0)AM%LtP$qp6NvYuTJfa*FYE~EO6G~F5K2cuy7qboF=+>jh#4bK;? zcE(fF9G%~w-A5^Z2k&%W^A!O4iUbEIsmy@Qe;BCZoCg>FrDjzq8;v^5FZ39d<;&Og z+Mj0ZW8#l#WCpW@k}HEF+nkbzu)#zqhBFOc?N~U@$fbs+oJ?WRmJI&$?!s#+x$M!? z?W-dEZAh(NUK!vb%xyp<^CDDJlwOHajk+S4?h)8h%4@CIZ}=M9NP;y2O|*Vy8&_gF z&lwwm3B9QpyE-*S2xwmE9q2NW&ci=V;2Jf6C`t;z)H2t4<}x zPxS|{?euz2dX=Dq*|T%Z&oF8)HOej)NDu@D2a8N2`0!N`*m+tCi&0FO;BItl0nFq( zi^pl|Yykj(rziFzEWxP^iEr4@Ty(4OkM%4G{db1gppD1 zKgZQvEsm=w0tLit_@?STcT-ftiA>@-T`Aq5GzMATTTf4T#Py6~b*70AFZt~C_t)Om zY~DA|n;klXdpv4|L?9dZO;{z$o3DBf(_c2y>swGOBIqrr>U`>P^5*8o@_Unj5iX`q zDTQSQ>GUB1b+V>e4IZ@Rw}v~@^MHFuFr5l9d|F_rG<161>%Ip+oyc1J--sG2#KTZa ztXxft*ozQx?mrM+fT?;xOirZzby{(%HPTaX&) zqW@5)q}=ADuTng;mS5Bdr<%uAw_-m_ZTeI%kkmQ~5;;+HoIj_4z)7&6sgM}+snerO zZRzWhjN;I(H`;e6naIZV>>gfGtv5?UlryZWzQc7bD9$4^N(oTe4d0K@d!dC;J5l8H zRkr}@lr4fCj?it(c4aB-u^-xE)abVn_lu`%o0v46UhFoVShVvmr9xbvoM$JI;0M<9 zEn(H>+A@6X`kKmOub_sYS#0T&HP!2q20o(OVxfaCQvVL&m8DXAHqu60t&O7_gp@Ed zOF^b7RY?8#32uT*d@i>EbceN*z^WJkrKD7vi)Y66S}H`4ps7*xG+k?%bZqcio%nG3 z-@ty;Gg`jqI)!);*r@;Q6BeW!Ex|bd(bqM&sZ5!5JbRt$K4c|YOCbQ*$oFU6Q=8z& z0a#-~r5s&c5tF1E>z+ON-okC;noGOrzD6a73Xcb*5bLB?|LoFyn6J1r!H zKn;VLiK)KG$O=B?uHJX}*rq(JZN3~_lFoBD3@uLjmnLB8*4f$Fq{k!nlm7xWf}@pe zRfAecz>zZuDRpq{f}0^9&Pv>eq_etQ9`Ogwt4%#)uH@oh^%$z1fwmYliO~f+xZ{qH zR9-J7m{D-g4w&o9jl^B2twOa@;bJW{j8aJ5^2=^{5p#C&QZVF*bCtC7>h0@7A^&Ga zlUMmdHf5J!@8tR{P}PE>2~RqP%i$C$fV@wTPK)HB2Ub)`Y zYtrTBtaU*oF{a}Y&fALKl9=&Ltq|0hopn-`7WHKYum?+*%5o`nPJow}tcV3}xDV?^ zTCNp78qFz;fg3Gw1JEIx>#gsYB-24yuDI=ZlL+5TA_ZRKGycrWC$n34NFY9DFdWUB zhge6)3gDXsHi+5nP8iZ`FIoti3=`YyRSM9YQXvOvc;G@&$jM1)o<}$^Gkdc`T#E(r zBQK0rEIUSu^>ubWOi(6+lf4|ovwrTuij>pJupXRy!07Vc=RA6n;YELlCH~T=3HBC-lxSiefB->82`|H5(t+o<$m~JW%hWOL))MHqtc~XIpJ}l^GH1T`!mk`??bO zV*T6{d9SjWFA&+-ZCuUcYIu?!H-A2_!JAEWbcrmn@pW(!h*Xm3P!>FNqPQJ+Ct*N3 z&%rM=a^pL>Kj_(NSiekVmYwH&-8Xog?0!Q09{qE~%#I^@ZfHNH@ZXd3mk504nXUUz zVFhq<4T#6m3P%MI1P#1x>jRN*m!4wD^OZ|;?6G+G0wm8i5{;?S`}nYue+S4CTf=lX zvw()~yG?l1QDfG8NoFiF_IjYp^rG7YVuX*Ha2&mG&3JufgxWqG&UVpRqMwbA(fe5Mo=+eM=WO7EcZ6o#?qI4hudkw=cO?3LlO@x2+fn z&d>~KqCD>--wo1uDz;SFit2TH7v9RnBR0LXl5S=9)CAhzUeO>zW|b4E3=l5+BiINQaLzT5q!|8gDmUGZ?X zS8&MmJ|r~)ZMWhKiIkCIyo)j>8^rM0Lrczi)7^qw{G>=$4zovBNVtd~d9gsYxS=^O zLd|!-m$;@AzLU~|!T02XGWM%luNb0iI(a=Usv;hY>K`AX0aE1@3*oQ)XrseFM6gN% zZ>cT?vAiFS-V?`v{kG+@ydU0=iLGhj6(?tQ)*7kxJ0TL1Id8&7HTyFZ zMMTTU)t|{lBZ-Y{Xv3hxY$k(bG-$PDoRTm@0=u_%&~m}N z{u}SRoj~Q~TD!BVFg$@`mWDy@E$YS%{~%Xtcsc*~UtE4iq@`+Xll(wa3|w|JEwNkb zo}GgOif#n5z!`ZKmX8B|fSm}FJ}`SMu9zkggX z5@>3$YEzO#hmu$_hlJ(JLkLkF;EQr5k-f3;;oA(+>q?vcV_M`}p2YETE>=u>D5>Bq|P}5+R!3{oI3mGtVCF20&SMxn!=&9jusMFiv|A z`{DPV2>QML+q$^0NEYf?F{pIy@_2=aenwimD#K@tX_)O5`FB@vt%Q4%qfM61uJ37q$k*B>SBa%X%B{==+sjA7r5IBsc!>^L%^X4P zqd)S3$Kk*siD{HL{cERM)O60~P8~hx$*}#p&5v`}^>DV5ubNTQHkiqP%AgcD2n{E9 z0E;vKvMV!qCt{O)@=qd0%+X>le>#p}Q7C#jojYl=)Ka@y?Si^2J*v3K9C@WKM<{gI zJ<-4^vzT|HJHNNds(z4$W9bm|kmKa*8r%4Mj$0V~=M@*Gmq|<5=Zm=Vi|atKbRR?S z-nNCK10OGLs3lg?H)>B4|AOO00TL}Su#0qaZpc|&W6@Vaqdpbx%C?GSY0B?z9?&VQJLfY4u_=q?io9j6ckeIet#gQ}+UguPSqv9E+a#_?xmX zKQ~^(k)!u5YnZ;=)@j6PDwi3zZ7KK@`S+@nQ^?aNw-Kz4#@cFx>{{_aW6rjCJ^;kkGr)14(2eQ zA+w%l?0C&wpq!dn?G#xgijafjb%;_{qu2YhBh2%?z83sLF3#hshsGucO!q(=IN+Gl zUCYhNrY&VS=3hhv4(>WhmM-YGM@uJ+M2mPu;C%dI9{CUxng3d5f5C~?DL2z`@ZAFm zR=x{TGiQFta?!$KeDRh0%<6bLaPc|`+-0!%VBs(-sJX+nQqKfTswk0r|FIbx9;z`UyCJS%2-oArTF-_1Yds8l>#V ziDxw65fqET5`dkg!_iH2p4~2iPs2aKmM+tXe%@0m$+-Up6+v8Eby#JgOh1t)jor)| z$+*uhx#!FBfVBq+LT|E=Jw({}3Mf$3SkSvsgVMz)U6%rWdbFu9TVyXN#i5K~77}P$ z`o1~TM$kgWEL7WV(4>B6J!)x;W^T8KS^ zYNq)*-Q>^Zu}kEld;^#S#j1V_&bD25XgDD%e259WN!?un&hDg|nW@xD)E2(D5TI@G zRGo$A|D>tse+K_}?}1UC(4-m(%v+0I*T^3_6%t%9|l`vucg#OPL9w zF|DwTB~(O`3e(X9eGdlQ!1Z6CuBG6`ryhiZ6x0q&O_;;pufS3h7*D zta88M;Hx*z?@{}Gf8RE6&0UxV>bY{^LAgGzXsG0LVE;tNXECHrr@>(H?nV5}`~Cju z{ITY|)8!hjx&E%xD0DwT3Hwntw%Y!6T=a!+^qjapATyhT`HChX&63yEc zre(3Q`l)MEp2$!V#cpnBWY!PG3RGkoI>v2i3$BIhkQJ&NtVahB;)CGh{L-pPPwZJjLJ{-}?UNn1q*5p(rI*E&6sjo-%| zgWR_T_Bu=&i*G)k%k!>N90}j^qdtrZtq_&PYL$+McezgnPN{7YYNYlaR56lIN93WcH({#Zf?Ld zIlEAw!99bqdl1uqm?U)EorWGrB1;?yL^*1JCU0S;7u(KFAvAPOTQ4wR@vW%*4d?J~ zYL-(;f916mAAhr{l|<_Ug7*z6a}JSc1_Pbz{?btE9b6C_=&y(p*Wg`B8+ajeCRJF zstLr2c!upmUp}5*^f->}0eD&3+9ZLGYFlSqeNR1-*oP4o^{pXJ9>;G=PGG6lq>HYXFlC|E zeKHe(avA;WR5X3A4L#+XNvBeF%P;q-t2HMl!GCun*ZLM9w&(GwuoP~w(FrRPK~ipR z)Uw0X)m8h&tl~=l3YpCvZ#R+(Mp5kXHU zfcoU`Nj}?y<^os5uMLXB%t5X_oO$WSvsJ;oJSHB(9qmpDx6sN#<}~m-K6E|0PKo9c zkfK}+;F=3Oml~0J5fc1$=)=B=~Ppzap~>44XR5TA&;HlE;CznajJI6KLkk8(#D18a#ZED1|Fot~=**q(A! zf~uA~K>gz^X(ur!0X4w|OwX*uB|6FfN&jQ}hyS)mzJNCle4VB@JySP(DuwBAUO-{_ z?8E<~=^WeRY#Xkf#%5zQnAok(=hKz|N`=bK>p9n$K1JS?i0&EJ6Zhdm3svA>Jk|9fQm(R&BseruB%^`xyKD7)i~ zNM0`N$;So!wmx6tV3HP(_V}Nus@wAcRJbk7V@pST2eM-Bh5^dD^8xfo`c(D=3IZ8er9T5&KG_*_)8#mEiC~cviI%R`lWm8_AfTiAyA=C@i_~UPQgw{_6WD{`08wDok z7PcUVVl5O`??fq0LN479#E2VLcyZg(OZH!GTZ0MzAP@{0=Iw5x@00_w*iyje>CBwC zQ>Ig!X=sWhC1__Qn$4INsw%S3&x;(!lDCSp8@7}kk>+9{V(Oyoj_ElY7J#FnO zb`Lb@$KMoyR)Wue?hL_%Ing$lkOVsh@K(ZG8NdKC^1G?KwmYlc!ZZkkXozUVXgDS> zHfiy|8!=LK8T@zT6MMZvkB5|pxye}0hmVztS#`;h2hK^dxriq6-uFYs+B`vX*eH~U zsLM-TGrPR#5Vn9E?L?vm+?P%|dGXgnrI=}40Ppb7@?4hh+^+&V2dS=AzazXMknW_sG z)T{UB<&pNkbxq~MOQr+Z(0PDa-V>lUVB(Y4!`WoWR^o!@cN+vp7Q9oq7)>pc=TmK1 zknSY6l0W~)BaQ#STje%15cQU;*fCe2Nz5|&OK5U)3 zvp3>1bJTdS=m%c#TmREvKRE%&Oc6KWrZj-DD(0cMdtgup*^cX9f+5Q z-shCln(~suSbvLmtyO=#qZacCJ6aqNCX9dX!M15;NHRi)W0+AmiL3j9Y2C zP=4yIs5wu8uD?#O(HB5PgUV=yQ!Zn=6BMzUZLe$ojzQ2y8I6wE&DnT=>%Sta6sqqL zYhJ-=A&RXbcP=D`1yUm55}3pwpDXBddz58=3yW|!a(jl3ge`}pd#o<-1=V4^d89FI z5Z2u9JOCw@qn8G8g5I#*(d__wFmdEWTb*>8R8BtXQb`CZ_k~ zA=50jx$@r3!$4U*1R5ooJ#N!L%mIr13ShAk>7DGL#<3vS;suc0j@59}6%1ZL0##klwU>N-w25S4 zYnQulHf!8uogMIxCE2@?i)DfUR-mV7U}&;ox=T9oj10F-YUh8+sle_t?+Dm2)u&>4 z*&!sxlPLVHJ64wMe4Wx9ANw#nd8}pC2F)2xNwq=A-xz2Bgxdg*_8^BQitMRjVIY+` z$KJ%1~Rr87W&=KdzMjl_bDM=2))vWDoX0nfoBJ1H>5Jg6m%+KeBriqfD zbZHIvp6tnRtL@f9(PQ!|CU1&1D}ZrhPmX1TwvS2}jWi^!gzpj74Y;Z!n{lf2)9I}% zS*tdPP?mP$Qoyfvf=JcWep88T!l_7aMqdgg@g()W#}X<|ZgbLJ-VMmeNy0Xzjfv7J zl^O-XyNz}GUR`^3xsLk%BMLWL6C`q%LY8_g>%lIy>GNvZGXOFdq0#T#_BHnHw3AD;I49=!`@$C50$Rtf8PcX28g zEw|TKjj&7f$oy>Bri$9~T5#NQ4sG5uCQ{|d442mll{3NCVBXR}9 zlRS|2iQcd3#{PiI@`K_K5VhXA?ag!jp3?1zs}erzynyG@k$lNhs+yVG@w)u}VnHwW z7ypj!ML_HMk9;3Tvoge$b?$-MMLHTithP81^*Hw!TIn6fEH-kqJ%P>+I@C2*O`{q5 z7)i&Kd)^~AGOoZbyx9SVunZ1X*4)&$bBjETbEn9D1h zIhT!YRwmZ5^Msc(s9~;evK&?7yPp!v&~pkbS#16|(?KKuyjdPC`KL>nU#<;NLC%6X zHINm&fE|a$r}~ypwfTNWZPxS7=js4Wg4r7r(&2z|^`_nkP7MP(XQrWjB%UMHw%w4W z*0MN7O_zu#rifnm@1jaoy>_67*HRiezZA4sHj?2>yeGUy<0uk{tR^g9@j>V`)HzG{A|C$r#Jo z*P=cb6TR_55Fs}6rMs%dMz8KZh`wCJ0)&t;TeYep-Hjt3sv@eLnmju{Asat>XtGos z1>dU)6baOe1gcV}ih%Wq_>KAuW=#JgL&yzfY2#4C6<@;6r&$dNuO!-3NZ<6}#PDY3x`#BwI?FXC0ZcCT{KQKnA@Qq}7U zq8OjX)|_}qifD?Y=)jUrjUCV6cw#ubho4@tN{rk)l#(~b@u#Q~(+D{UA>!TgIu15j z??Qv-K~hYjod(ElZ8Z$*BndbnXf(Njzj$yEA76bsE<{=><^Fm!6U>1dyIdcpP6nnv zR&D3!6;Po=4&pAEY7i8U&!O`|6_bF^i$DGUpJ{m%pZ5*qf5T?YT)I-OT`Y}#96L-p z#1eA9zYXjMCyLKKXm06gmc-io9E;M3J6nXnWz2AHu)nVIzI z5aVwGr$sx?wmLwBWL=<25+pM}ibwdGQZU-j=J?3vQ3P}{TmQrhibHd)ca?~Qr1OWB zd4&RJHMm_Yqx$e1(L=J~KARy1&L9V)B@J;q`khQpiLGQk+}WSHHBPru$IqmgzK=gnJb4g1{43GQIb>Ja-^9gie$xQ_A4j8M>|q8;-#JjOe->r=I6& ziM{XsSBLitOU2gq`{ed}-*_H*(xLuWmA%6P8NvA(9pPK88DT+UJ;#YqA((mKzq>(f z{r_ZbqZlM%U!YmWH_OyoY2=Bdv_WDS;Z697nZYe^>eF3CegAy4%HN!voG6d3r@AMu z(;%hd?B}=kfgbaIAa^^$L4y$nfqCgi`iD{n=S#%?@!T93C-@q1Z`&^t=ikL0+JcW6 z4|(xe{$&GDG0k{dm00Ys!`hrFxqmjQu(`m)lDxG~&BOOMo@~EUa;BxNpt_Z`=nyxg z?%6o8>}02)kqe#OrsE`J9`j|~{a!8q%Q{x9_A`YD8Rr`S*?7o60>eD+0Ag|>W0QH4 z$ErpWI=x%7N@`1_$&D=^gYzv6RMHP1OExoKnl8Ljf3}3fBgslM}TP4KJAk5q#?!*O-cOCB&`SbER$}>1~&{ZRg6+y*>)8w z0#vL(w@0zcZE(u?Cff$slLgSz%hBZ_1UX0@8mBb3xuZ!ERUBqt>q}8fC;lXVCGbWD zfH#=q#r#Hcrst{THt)`Ag2+FtlLr{F5x+WGDu$pWu*l);WF-C5)YA*SXBx*-RFP-7 zQXzmyoO4DtcPNuBj)Pv~sSmv@RS&deQhrz@(}%sm zsM2G{z582H=Sc;hGi8F=pQ|W-&;8w(^b9(Q=+J9_GXB+{S1g=E_Kzb_PnP^!?<1In z5UV&L=2EFZWy?R(p`?_#$NGT#M=()J-pu6O40^eC`Z)ig|1eW(ux{U&`jcR_V!k~6 zU#Yf+kHJ>$DRTQjwfSsW8zI=83{pMIoev8!Vj=aB}+IVEf%n#bkkG zbSE(=H9~WVkG~n2v-UwQmQ>PX?)l^^)k!eHczBL6R1eiPeDdHhJLzkXeSol)7KWZ= zM7DMGW)i^gi&ksj0y9Gj3Gd(CTth)_n$4Mq9@?j>Uc_%OI)guQX+fDPMi)$Vxe)%YFV?Ug^r1sqAWI_!<-)zp-_0`UgCJ1tx-75 zn^Au-084O|D12-VODh+OY&ORu7rSKL`mD<@NOi zWq6{4??4#U$xb)71|31TFHXW3DXV29_A?YKhN#<)V_>5tmXnvETJ~6-u332t-%(+@ zijV`7FRE~uh61D~;o5J1(fKKqyWy)XGEHyPqqlwopzn*J0lvl5K&nyIlr(2n>{K?l zvJ*kxyjIN3Zo&GYT2qqAu+pzoy+m zA%gPFzxK1t2`(iS8=FD65A@RC>DXzW2LKx}9q$#(W~q$o>fecBQtF+(%`a#6@6fsj zeS=Q_nM^VX8enp13}(5L>s;+}HWXPb+$YEfE?4v>?U_Jtt=IWV(yER`p}=lc5fx_oFrNni^9dO@W!6Ti!oKN-Hvhlx#Zm7?FVQQ-zk&rPZ;7% zyvtMmZdGU0A+}C9VheBgo@KS2TBn3-&y-7oVCcz+frgM+(cpvgSs}TM0%ZOY%`s>i zRxwdhHKa*amj%pXj))xb@4e`8;4ZeQ)~3XuFfQMn4n0)gtXR-{n~kn}9nE=NZ}wyX z-yp<+p6jan5t*_OzL!S@&U+mQq_Xn}yrmQzfV|2=|_IM^0j4j%< z*5*p1?sLdOm(U)>I$8vfCZn^N#rjyDGKO4aaS9#z5+ZiRY(1ikU^!EZ#6W&c%aSBH z->&F)^O_nR)VP$6F{ViW6hhJuks1jKMTor4+Jq1-2^7QKaz^U#0qen+iw+G}vw=F6 z$;3FAR6CqWgQ#=w(x1fho~c-jX0ydKCIO&}?j77@BX3Y2%&}yjO+AMcdyJxUn0$$S zwA$)T+smy-lQD7S5F8k)yqprB5OV?@nE^sm;pyBoNK(zZStdB)(U{VR+9Ana(-(l| z-5Z(L!+jeH%ze;2Y_piC&+Dt3h1zuVjBJ_B-V^kJQYOre`E0VJ!^)i}NZg-0D4#of zB~f43_l0;f~-=|oAWByJsaG(iEuTgHzr!Evof2kFERmMSrVB> z7{>n4+=P51Ok)AT9X{y$V+A%0{zy|QB6M4Y9c0=ryLpoM4elE;9dV<;RNg#@R<)0 z0O0yjOAU?4p*Dzfut!X=NHs&R*JIRjhJpcB>7m8?>8;y4ug0PHcYVKaI24pp)SEQ4 zQXQnKnEn9JEBubYu?j{Fgo2m^;@eg0^tH^!WC8K*Rxmj4yWq{zyuZEgi6kQ%3KK63m`KB`F*Yh>(VV+u4x} z4__r(yJY>N5$)XpORdO)*A_tlTO)K_g^^w<>-`rVbnJ$`XTbxDuZ(A|gP*p6sS}zb z`tZ%`Vac8-7UuIK37_2(eU`z1{>EWDg_$Kw-?>=DNxv&JaMuV&C9FKorxs8VtKBNj zQ%)B+HcllT>WYod`$TAlK*mmIU?0}>ChV6VG%PZ!GZV@@7Cv8=fdj-X989c;I_!au z5Swae&%z@v8^{GFs--1iUcwJf6poXI327yr$IM4Z3-Sc;eJkCSQ*MGW1lAOhvFxCq zKFLf=wXo+Xxbko#e$3+h&VqqqUC2$al@MUU&A*?P8sj%J7%}2Fg-^sWjFfD9x-VN? zTueUYT!RVgC;l0uW=peG3tW?laJOnl%qxWnC6}H?`Ek_u%B@A;b8g5FVqz6M;xj+6 zrAv`Yodh11p-;&kRNf_iy##cfL%ei!W%o7pnN&Fmlr$=P-`E#5qv=ma(P`Es>9!c= zc0DMx%d_8zBa^5%NVN_T4zhEhnlub_qP0Y&tCO#0h~ z;-ibhstT9QL4RRL+kr`Zi2Px&yPk`FY0+^_n<_xwA%R9ov<3{P(I6TDz0G)fC_!Rg zghNSyk);(ea!NQbKOQ~#iG8wx9gX9YZl! z6b95VNt3tJOTceNf3SbOnBhL?iWk4r%zag;?`CNIS3DFruY zctDa1%#G+j_6w&Ncz(H2@w$_TP)8gRmpl+cfZ|x;G7sv?5K7TRKH5jTZY{lAd)95k zZU%I+vfjD!8QR*~JY$g1d!}1bY8S+_@N8lD0H?rUsD1E;L5L9Ob^qk+KDsYQk%1;A zixtK}hj-9$JWHSyAF9Eh$8wC%No9cBB0h-JeAO*GX@o~BDUegdF%b)n> zD3$ly_*KKQE77psRQx28D0(aEp=cZy`&QHif_{NjXrscWri& zE5@l~YFSctEI}cgg0I70@$zlHhiA*5&wl0XT47-y{!=XI`jMKD^wk8)aC9**DkD3g zJi-U-bms#G5Pv~*j3HPQZnZ!Z0Ke@zvL!@?nMvO$z)7n)40JBibr%f30Ax)`Iy`64 z3UpK9ktvL_$0aU|O-3Z>yj1miob+W-=DL&e@%`d`JTX|eTZj?nXWvkn6q#a9=-wM> z|FbzpkmKo(Cow5V4M%11opqUgl*Fa2F5~?&{QL2f-}BPrBO0y{fsdp{j;!dBv5jk6 zmP2>Ht6}vl8{Il)rETxjduvq;!-QCD;}pDr;nj;t0epmVshp*_Xe_G7pTEx1SU;;* zli6g<<}I8?Nc6OIw>CD4X9XJ<&aav8QW*!Ra&2eV`QHbOK^%iAy{{STC3`!2j^Td4 zCqncpI|{+bm`)a%vM>XB#yy#nsW& zu6T=;=1!9lB%E*a$r=^G(vs!hwBZ!9vn^ZQ!9a2$9w{Man*6%!M`-VD+TC$($&!l+52`+K^@rr1virX45kfGnE5rj zNTZsZwEK%It&u@oWCy2BNCbQdhn9xRs0bN22xeZ@vN&%#Mta zW*cGGx?aU=`kI>R%O5clc5c~?%6Mkk^{aJ{SDT&7S~`4Qj~69jd6Hh;0h9bg*?5i1 zo-Cfg4iCzyycMp_8-C8@WkD}>lq;iIutIZD%)0vu<9bg|#ILefBP_A+w zbL<$6@Wd}H#k=kQ=8z@^Wv1OLfaKM!#s&oUMMrL&>uw9)hK62CcZy3>jA;_gbYME260qJRkv%K=MQww;p$bHS(aV(;ap={{>MORiIINDykWa6W2#`QnQ1D zGu1zW_3U7@Q;v0XIa?_latYKBk5WrLL_PCOV9~Os*G2uX2nn*bzJ8Jwp_7BDhh@g* z!zq9XU3`7>mazZE4YZP(#{(LxS`*5fe_h#sVR)Wgf9$;7-+?ZiiS6~J(6A=g=vKZC zr$5F(55r72L)@7LC@@K^Va zZfFrox=__-c>rnEvR&=H=Y7g*JlUXSHl*;gy8S1+x)+pT^%jwQU+M0GkCJI~3ajScF0xucd*u=C~$;uWFBT2g@AC?Gj2$F^1iv|xrf%XcqaOpR(0iX_=NXC0T z73^G9ENEe`DHk}-&aGpJod<<+#D>&oz%n_058+lEc1V`X!f%Nh(jM_^y$cS5U`Gr- z$3iePaa6Lw$gQeyu(g;+UU%>RZz2eWS^f+Se|*+AO#|ULrfAEJm9|UYjhNl)BT30) z$hmu>2=LAf4aiEFVS48Sc~p&({L|%ekX!58z$YguS!=BvfBgX>RscJ`^L*&^c)zTg z=RpnAt%4%u(@qnNc)1}+Oqe%|1>t2t(E-SBDVs$5XsXv@ApQtl8kB`iLA)*-5iHNI z&P!hr{+0sLanVGyo!h1A0JEk-8b~z1v(g48Owi(sgVL$p!fTTL)l1j1w?wy;rD13s zu7oGoVq}h(gt|q4W}lg`UrY_8stiwF4v-i|&#ZSBorJzUOEx7{y2JrZ9w z&g&cAwd+OdJzifu@;hJ@FpbkL)5^qX|;zY=k zgXVglbUE`6+~aE(uBX{$xt@`HDe)B@9Nx&&lAZ#j z(K+l&oms3~w45944kc3&8it2$9xvcW@(%pF&xZ}&dkcOZ7{pgQkYt{HD11whHDSIxCGvvRUw|M70+dgg!QEu zhph!GrRH>rh|%^~)}rckHZqc(I-6By?Z>O`bepDu`PUWrqM3k++uXVx<5j0X@>O8hKNJb7d5ucM4cJ z#g4eHQ$DVl|)I==M_gMjz#1YzJlktsn3jb!C6zC=+k z#HFkZ`V!DM(?u~zJ;rMBWOW3r`Q*nje!@KAgR)uZ4$OZ({q%M{{`a)M-QORY`;Lpd zvrldCu1py=d5fXU60oLs(X=>}BWD^fdQR`WZqymCh@N1)`a{fNY{FNH;TP|qs$NFJ zpw50N9*;uRKp=DQ&&Y>!y2WAy$gTbmcQcB88+f5idgpq|whOw+ zfkMogQd`#BGU^PyPPKCe#;>HW9YGUs3LdKtoBD*qX`&umW^rkn6-tP@e@*kJF%r?_ z6izS+-eBSFWHabooVCdW$;#DV`cb*1R~0+qUr5H7RN%G-%iFLH|?P)j0VM zlrw<>v9AL+zce;x>Su{5{bGz#b~94kiys1C6HZA~#K%hyJ}hp&_gB1mZ|}50Ih*>P zFNYx^pgX*~tf;6c8pR1tvrKDqo>qHXx_h2~mZPWvnO_^ndaJ9eFQW=uVJQltZeO21 z0A{d2a)oq(U-s^JqEyi{2F8@GI$L z^I?rk9KCF--WP&mH(|>)WTUKS5-~#pY0Rr;wUgm(@~wY)xZohOr8qoy$pe3kG@Cdb zI=$te1zNp{re#8e*XYLbO)pY<2|F5o(nbr8O04|o45^aPJLRvcEuv8o;^Bl1`-Zv= zsx58XvyJ2{V8&-~T=r3Cm7W$f+`7`rZW2P%c3^R%V8z#W`Puf)mLV*xqer9Cbr*H%J<5$c4wb6 zNhU0=lrQC=QVpp;I;i|pz~9}(XAxnU*ZAs!Q>0n)*!Dii=j+oL?j-F-)@ag}fak7< zl}e8~-1X1586q1FgYMP-T<~UCGa#&KER{oCt=cv}``bFMq^_8}Oh#S+Z=G|{Dr4bG zuy!D$)?t8LKnh~0$wqSOxA%W6vsMLgSh*S57{JK|oSn=AT-fis>(-f~O^83idk?^G z*-QgwPWisx@ASW3m!*V2?#GYWTJPPc`(2|}32cC7b+J0GZsb8w9jV+1^=pX!bBNov z4>pl6su=h+=R*ykF?WhGE*8Kl03ejKewaH{?Fe^uP@F`Vacp)D36kEMI5{i`a)5;q zdiDpvE#TY-9#lPriMkf{#a~5Tcf<-3$pu{aqZYXE$s`6D<~g6Ug=3|uD<`!cN5g@i zaE7W3uuVJc!LDMqHy2~lGZf_G21kt>%Z#Z}wWUX9SBa|P4e$*%6>EU^-_cf0o_4l4 zQ{&5VcgZ(Gn6dLT3SPAGRL}mMVQ#O<>e?P~o!0H)l3VrhJWJDazZt|vDV4>16#T0F z!mo(d^ZMKPq5pY7t04Hn7Q<@0{`J}WMi$V}`v5Y+<`TT=zcuR@i9bB9+tR35QEDF+C& zH8r`MKKr0D5j);?cZramQ&43SD{Rd$>%3~IouS;PC^)oss|UYsUna!mBXh{)U8kFO!Vc!tO)Zwg6}O*Rqf&yI(vNtzUv zl1I{gw)_3>ae;)<3JMizF&?}f$Ey4LyEIL3jPX*n<`P^#scf)#5+WIqN7ToArt=T# ze18Vz%7rZYQEBG6>8eJO5QZ@+Gg3$}IZ?q~2<<*|d>|_%aej#b*<8vl7#Vj^SU`aw zS|(|_^8wiYw-s6}10u~}+2Vy$hv}3c2%aBuXuu@UCnJI2J~xiF|obKVx=5iFkkRnLE{Ax#5BPEqvwiDTRNtGP@J5Kr8<@O)ox^SRtw@pwh&D zmnqrnSFXvDueu(%Lkb|@ebR)PCwwk`iJUMkLKs~t7fUUcJT!p>0QBIvE-8q0vcAzb z%!C-x(vq?9U3I!fu!Gj%mum_ZCW1qur8M)H1wgwERDE;580kB@VB@ThMnOUGNLG{0 zWN~u)aUOZGR`iz&cI1b8Ppz4-@J(8&)6BD!VYtWlM@6VFtQv}q&@P*?z^1sCb*A)| zpFL5(v&=6m)r>9Grn1h@EGwr}Tog~}EFNa$krPYGv)E&UVqEG(MQvjmD&iO#7s@or zU6fxYpss|}DX|1v+kl}B&PwGPTS{|j(neK zgc%H&5F1wPfU6N&5t_fbClc@mbt7?tZTL^f5D`9tS^c^2z?Gz#D8^{ksCO;d86CL0 zq3l@+n}j7RZES3Wz^Q}>W=ej7_4fKn_Au%Acw#36(`zMdKMVFo1blq0c+LM9uQ}JV zxn|ueII66gCL6`0GRWxW zvHCv^?sfB%RxkT|YF&tojhgm$zywi0bO(6Z&R>-4sL3)-F@XD_y5Z?`Ubkf)j3vSH39tmr_GV zVBEjC$;{6yH#3?<391*J@)SEPEiW_bbxHCHs?gVQ@;4k5J_%$a|(6u2VWGSTN3#0jth9e%JXX(Cr!KJ^KBA93;lQIocu5LZPmMlw@0_|UQk-xzH)p#B4!Nvf zS{5tf=OT4hAF~tlSQ0aMCG0Q-`UehYHdy9yl?o0$(T<38>^2Sv1JDKtED#}sxLcdaO{tZ&gdxfs&3b$H)YZvarxCbhIbxu=p zipz|}MI*!AkmEcuQ`g6fwKUKQ;QFhdXcZm>*PxDXqsQTCKJU$>bv`mvOZ9Mz10t@5 zNp;3YzsKFd%PGjvymw=BjUwLrY@;1iZMrn~Jt`w())%-KsndESppYF3n^xtv@F#22>TS1RE;3jNdu?B8);Ui{95;W*zS6J)V^Q-kAugz?63er zpcmxC|7E%0b&ZiC(|o;ODE`F8KAOto=UqPJAlb03GIHa^<-be?V?Fins2f?DE5{KRVI`jn4ZDPvg0>5U<_O#SGvv^fkq@@=ar$c=9}|#C)Wq>jN}rkMx)g0SiuC3` z_wyTR8&~Z<}ai%|wvkFvrJeN$ls&rYk4FcZ%%Y*WkwgItD; z!O7x2d9*S99Tx5hWWye9`4)O#PjF-@)fs5iczb{#DDEbZt~+&Q6TRGSeD^+~q#~}K zC)lq}i}drnKMZBN*G*#1jMC=x8kBg@jN;yt3a^EC<|mZeIoKrm#+-i(yVw@G(GW>%6E`75&zY-4o9A}- z+!+sS=IB%46j8JF5)!+^qEt2DfBG30zGJ>kdr~3nRO&Vwfm!-n#Z}EaXQuB%RDQme z0;ydhHl8PAY&&Hu!A~~?pi69P&{!$CuuNrARMrJ#=M!vNFO}z6$qTk&O>O zDxKFNFeq1|NRq>ZmQC`LUiY+48~VcY;hNF5Ee4sY@5E>5b?R!b#}&u41Iv>+~Fv}Z_Fg~j@%7Ov5-4tip5T; z$W=6OREz|7bMNi^OeBF)E?e}PzI54 z1bki(+HmG`Oy~MTf2xTI(N6CS5|_v;vt)iR<~hbXI#oC4B*fZ`t+$ z!T(csol<=jf6&m*u8l$dUjn#2?zdhH+D2#m&TfI$(F$vMEJmEq!RCKN>J#}`S>;L1 zoJ&7G^ZY)4FbKXNmWAhO?@JM=w@VL^Q?tuknq9>LYZ(|MSXm(*)bqNYCwo0!{5}Lf zK>}t=W2fu1o@W_Q0#s%>3%aIg)$?=m@i~uC*9SFQU%+<{zOM8?p4h;vGnQI=9;$o4 z9=C5gV&_0H%KL3vkC3R(RiB3$t>irCw)fpo4F3Jp>yRkkbQJcq(>|$O=HC6@1|Q|9 zn;Cb8hh+eJOPl3Uh(rIv!+xCL%@}R%zy?-=_JH`@MXoG9mvv=BfrmnRp0|gYnH}GW z3=bQn^9*D>F0s7)R*r=gYeW*I;>MJAV~$-`Mm#0xoV89@w+AS#x7G(d^QEUin6;A9PkUo#_fwDb2(oM zevWpq3ir+Df9s&4);=bSo+MsZ5up+Ztv4KpfMR_Q_2!eZgdwobqC+x6GbA^iFsBw0 zo(Q)R%BuNYCTAhlnlhIhXPc>v$T8Di&??9jdmR5;yWmg#2gGT%a+&-rH?No11!ih; zG1a8lB%R~;`oV*+P1i7C@ufr@>SaW-`u0SX)=_tnF?;h7wEf31%~%<0d3^lF*qR*s zEY>Soa#P2#P+O1Rc-9s9HnO}^m>1WnJ7P+;vtXmW)A4$w5F6EvmZ2C70J11a8gnbe z?_5=+cDQ|qwHbWa*<+d$isyJQA_nxaGdls-cOOsNWrpo8=U7NAF*t5p`1dFHQo0Uz zo)K3RO5;4et{o0+g2m6LuTR(8*dkFndo+uWkB{YL^4Vq$)e>5DO z3zYKJIUtRUnZqXtUF)wNNS#5>cmrZu2fL8lnZa85-WUB4S9w`$wnk_~IB^_pE|nAA zzTMg7|H+227lH?5G=(&Le0p>C>fa47y(&r5BVE4&0hQo$gpTKvt{xuSFCo2NC3spe zBTU@s85#Oyk4GXbUUcy2z=#?zSrj1ZCJa*}A)aG!gQ}7Qn!C6p3MDy5xxu;bJV+UL zz|`RMp-CD zu%^bn(mA8b#_C*anm7?;D{IG|JD|PJ?^%Cz?bmL#-8&v$PnyFl#A2_t>4*(@&#Yi{ z5|rC1W=i(fqd2jq43#p^<4FLpP7}JuF-zF&@kG(6rtL4R62IB$c0jg%>%Uv7X-22O zu4gYm$Q73*%9sG#PiGI7QtXO+H5@@yibN-rE82h|RJ~nzToq*oB2n5FJ69lJGrS+! ze^P|T)_iR}WcjM3rKNG}1KHM0bUwGPKZr<}I~24`Ymx)ZD4oJXpsSO`ZcLc+4QI=N z6eoHJoB?rR#wz5vm4~MN)9!@-xNwgB@A~|CWIgMfoA3VZ9)a5RpmRerolFgA%Xv74 z>5RWLRbM!0%6H;~!Uujr)l(8;YxaW_)TYK%rs;qG_;q4IM9ra9!-Wv5+^m4 z4vo1qUB;!QouG7SeoU2W^1p%UJp#!h$TXa*p<8;62=g0CK3l8MM__vGUhIjJJB2zo zr(~JamFRO(|3fv&5u)YmR{iS`^q=&($M_l8b2ACL;$wFJ$pb-n!`ICxyLda&9C35C z$SPI8GuAwQP_*~HK`J%nwQQfj<#U&{{ohvx1`i1j8y=E3A>OFjf5ExWPUl~bZ`fR>PsjM8tR>-#qj-UL5}hiA!l zu{uMu#%JSVUdMhIXqzRDPHe=WJsGK@yX-+yvaqZqC(S_8sFz@o8x|rg{N+GTSKN$U zTPMusZdYPA-Lg93%@O9#&M9HVI0`p2liaOl?<*J#r6g&x@bT#;H!XzMRd{yWYn8M) zZ1EC{ATV2Mv!uugmMc*uY}6)V%T?VvlVs5o_mBF8K#kduGYV-5CjvroBNiL+kuGki zZ1j<&KA*K&=&0y$5^_}XR6k-->YHIwZkz=Fvrn#+K8B;TO99%MswAY6Z;TzuP(h94OO%EYe*H@T1mCaJH8${YM43n zv`;#yfH&PwX@LKviEVI|al7S-vHcN-7hps%F;2XlPYS2Z>@oH#5gpzP1JC zt>4kl-PKexE)s!Keh?GpDb?(F_`^^tKhv1dg_+8%M(}Z)Ks|XdC!fd6$38r1a#}&vq2{MC^sP59pfcytnex6J82j1QhJ|JR=(TP-=mBGL z(7KLW!^(?d#a1;%wrhCwZVn)UF$bXFTtlnipYN;(fqv%Ar2&Zkz z%4)Jyhx4n>NOC*5VL8+^g)Up`?3DstLvl@5yv1gz(Ace(RL{0a4s_%{Qq1)4T=j?#Kty>Fs|6yp6Ivr@#Mf?Mt zzj_a>Bk@yljT>D>d7c8OUSu01`b%{-Bd6qViK3vNYs{{ZC7~`mdo0zY-@9CClr{bdQv2{Gv)qnFo*af%fCi3T*LZs zb!C8NkAU%yXX*A1IatKYJb~uUP5Gy%anMo1)wM;>eHTjW`+s62GKjytDNJxlEtTz- zhKg|5gy-{sb63o#P}NGDd7AJs=GGERA@oA)Be>QW?|8yLLH-}Mfi--I4ak=pN^G;T zeS{gMDT6wJ!lB~I-!Xs@CiL+)^_^dJi;6*?z_Mysv$>QzS93#$7G6%7H#5IH^2ktA zJ2Q@JS9v-{-EB|FWrDQQl-AJ>)Yq!Fi&XyhCH&~L)JA!?tAjOMPf*AG5@3(?1Y1$r z`NSdkvUmLI_3Oqx-T^ZVM&l_YG?PmC`RJkxgsPagiqch&rJHzWahj` zEUK9B|Iu`gQI+uV+RnDkoo(BmYI03A*)}KJwr#s6O}1^@?%mHh@7W*wxYug0-~ZNy z5n6PS2vFj_jKqS3o?G8UT0WCA1hqlO)swd@vS7NcnV<$Dq0>E$0;^yfAnvH4bhxWc zGLm{U>AQY5(qB7!9Pr$B<^s9`qLq%xIwv!KLH{1*NoI8Dq4Ga87zJfqg%X9zumUgT{g;>NXJIZ4Ur44FC6{44 z^^zth2Z>)%ebIvs)(|+TX>}EdN6k6I_CKzyXk_*Wb58FL#{jZ}sY1~V2Cc9_2&=3G0YDwh>{Cmdclfhyz6{oT&AT zGCczL5wlyRHP+ymht=JKPiMyd*c1qlk+Av)#J%rO-9*u^@fwP`k{4j66lZqHKO)^V z>hDN%`qE15R@c_ZvOlT(?x?7ga)4Zhyyfxn@rUU1^GpM};(H*$%tM9t=yBD%NfEp2 zYpe79J+XOlH9C6h=nX3Sb+Ojh#m7gO^4vC-`78{IS?P5Z2u7D4p5N?rJI#6w%`BQt zNj*O4+)IBd75Y2{>T|BZE8;)fx?C6U{y!&VINhmksQI?J)+c%*ay&J+NJo|}q$IA? zL-ee_VseH;$z0ST!1vkB?>XHphh?HchwMr8xvPcqoLs`0)u(QG+xNQL>UTrM6vFzI zF7DtQs5UEh7V#-*&TONX?tA9e@;8Q*Coc z8ry!NRrA4713kNtdJ8(rdGrLlnQ(>c zYl{d5OBBNTIbpYe|NZl}U#_pv>p|jwPCf8&GA}V_@2kg%EPA!4-Y)8la@FfW-s}=Y z3m(Q?;fCkVC3738J{>R|4NPT5+ipUZyJyT{trAJ|6*z0dsbTDVHA6I=|h=d^I}i}00yrKTj9d4(5kS##uH&1SLnyY3INK&v1A z^$baBjNeP(jtH!XOn=05PN)xTMgX;7EtY;WT9z57DBQ8S^4wW(BlToJCFq;COSvxO z^{Cj%qNu5Me-V|LQy<8#bQhK;=IOlr}!@lIAvV=XAAQqAE&ECttZ;-niag_M?AX5DNb}l1=XZ zIN-;#Up)UIr^NJUFnUKQOrS)OmELlOTgyqb3{p68YQbm^tZzwSyLov%)kf%kZ()%7 z;3#u7kuTQMN5%5ZCwwIpl?q#&<@B76*vHn%$tkYlzrLRtkzYX51ioGO=Rd!Xf51Qz z+VM3#6FjohD_`$DUv2Lz_y{1|<9@h0*6(9KDDnHr?mLCE1Sl{#S^1?Z{?g6*9?kub z$zWZB>a;lxT$IIMMyjSV_VnOggb&}R#0V`B@1m$htW5io-Or`P59Fw^K>3O|vRr}6 z^}6C&bFtg%l5p#6XaIvm+)mPub#4VdT&1wU0pB}09^Cd3@lwbhc+?r4KcD1tU4P06 zM!9abMDLSY#Uxp(|gA;e~1b?0=!o#AoTO*bu6k2!Hm6V!W7ZS0i83r>%@kP%n z#AF#3rw~#u=4z_BhTx>uBUU|E2;*vMyYn_y#)*O=_K^jaSkJ&aF?HWSQnN#wD!a>z z3;AIXQ4jhau(zGIv?Mhxy2O@|hpVbAO&!hOzs69rAb1ZC90}`L>!SpVF?33csu+KD z1<5zg0}Td&cHYER+n)C=U~5xo!90mpfpT(g= zI(A#MXlggUujH)@a$e@JU?QpgTSgcYGkoc;E}pkuSQLVKJPgs&&fCjKls@Vu&gc5F zbVngGNdASmIcbYSFgRO<+k#+N87=k5&V{SrvGNNRd4s5|KUJT5vN zPuQo*`DF5 zC~8=D_e`ITih5R4Uq^t`V#-dmgq=n*#GaDE-!$P9&bojJfLkvrWvSHV;`S6CK2A7^ zjL(mCP_PZmOTt-I{l@}5!!gIL0Inx@0@9lNWT$DZc-egK_BY+QkO&uKKfAZTnUr5qoc>i@&)e)RYDqxP0Le#F1e>Lh>~>*7mN#~(9VHpfzWMlq_zSJK5?>1LWRA(a zGJ-DSy~6g`di|%Q%kfdJ=Mil<-BFScan&i>T4NhCUrd8~PiODH?3y`avOUb#Ivm%+**huCH z6mDE|pVmnMmv7`>{X*t0^cloHbrSABA$?6c4D|IpV4^?EA({-$@OA3`8l|;EHB&c} zQ%b0&OX5Yu6$k6ZD+t)2gNY<8NX!43%FWF^R%l7;800tOBtPcns_|pO<+)Ser?tRW zO9+VVc&%E{a)_gfxGYhU?E6oy0zPRDrYxF1f09I@`tMeFYPF8m4MhW@Q&YCLvFBdu zqKGRgcf>?JbT|x8w(w)(Y-uaRZPn-Eio$)+`P{hmJWO1YM>_ynj%8_?&DI1sOOAHV zYk|}5qJkh0D9Qj$`J*nXe_Sr zgT=oFv9QmJRZMxh=!6@gWrbqXPNRhd88>sh#9w3Pvce_*KKkNc}1h^ zQ(aYR(JIaOhya#yEJj3tW2*9@)>{$Iyn%rljI-?|Is3j5ugz-)|0Db0U5qAoYl13z z-{?2V2NIWDmC&i%v0d z!Gpa~gOX|TW*s3-t|}7Z+s@_ez&m$W+{^02?c9j6VR>MelzXXz$Iu7ntn>9_ z``-yS5*O&OuUY5904~?;QIO!*_I zA0Pb|-~amu**jo0T_12TJ7AuQ=lA*LW-7-i7JfQ;VrrHd)t_qdE zB2xZFCV?28lLQYQ1&;8QDNPl5Y#I2)QubG?le0YG?Z~!UgRL2Ln+*n5YKLWWFPGy) zlpKjB?dHXa?B`cvSnhMU`o1!Eo;3tzrzzM7j01T9=j`YKJr5Y{YcISVW@wlX0tF06 zXrgZKpVxkVK+_TrM7zkN}0HDUz2=`sP^?p=i1 zQoDS#BayJJk;ogI|36xQL@1+&<;1qhZtCZ>HPtnWX2S5T?Es2g`h!y?6P1m8l-)Q# zFlro50Kvwx>A*I*s=9W2?bLO@X}nLxVJA%(Zoi-MXmCQd$%`R-3$Ff#d6}1GhLt(55C<0Mw zaK%18roWXLuxvtFTSa8phbZmasl!&>2e&Yf$vCi$}>suLrjL(SaMp zH~n>lTJjZToay4Nc#OavaU3Usl63RO-t;GbX_>(Ntey8h{xh+4LXPh)Tdrv`&1{Qw z7J+uxmqY)c#01``gLXH6tNrdp`}N0VYw9u3Bt7~L_4~AgLFjrt(vf{Y(Wr{{R1$RH z!7gs@Y?Xo2h(!42UbJXgu}zg>Jwr|zyfG1&O#5@gG_HcK12#ALh#0WS zt{}F%?DJ5j6u>OB?el)w3XG_{Y+n1OP65kEaFeJ4~oX@F#P)acm&e3D;T#ZkBXo;^V z>U(hXIeM&e_U@$a6N4;xGN7S5Ea~SwDTM3`6|Bkz{wNw1XkO_PJbIf3Pk+mbGKB}U z$bQ0y;l*2(-W%2pMomo(7`a4^mkqU7{xh@{sMVyIl7Vy*yHderx;vKU`S&RHpBX>EZx#}N z#X%pe>5`9@Hnj}{Io0er_xJbC-@lHRTG-Nk_=(vcdv8@0e`e9H@yPViu3u?3H4%X& z32OTJzhguB92FHQ#aAIgB|04|7Cy3okP7UKjmh>-pAHVp)=^hJZ+S^?`|SSi<(uES zzHC|3Qk%~hxrKR=uIkezL8DvDq_Kh`ML80Gu++uE`G6}d_27<>1tg*;q3PXM6vHnn zlNTj_fUX`6`r$cSzG6>_uT8; z{wA7yf40*HCej7n9*w5w8?UdPzczcn19!t@T8^->dvAuAQi4f&s)~#E{61p0Nffwn z9;b5z-rJ|WpMdt~bORPsE&zLl=jN}x+(U6ypiEzvd{(dpE2Z>fA5wA2-TsUzfG@ks zHhqtpH*Ov@)^9&U1C(yARp|Yq(XQu}^51UcZ&C%buvpO4+>LxN+&I`hiRR_4*?!o0H&jq;CR9ogt|qos=wN0KOa}HP zezY8qawx05Zg_;_)ZR@l@miTiPE5DqoO2&ctlta9S=iEh-#+&*Z{XWpNHEmq2We2{ ze9oV)ziJ$=bOh1Pap*z?&C5Pdcs6{ZJYnYc^deAOh}F1TBs(P${ibcO8cmBRFT5-E z(Z!*t<1&ruWa59(-R<88P^}d-(+yq@+Qj)(ZB^A*$ck$wYZ%xijKi?`cdmBBma$8h*?uS~YLzku zKvpqy6;!E~EC3tXFUKHawW}@8uvf&?B8L@DrB)CeEs60ka}ZCe=q3t9{8@tE>GSTI z;HsF#{pYs4*vyW;+~=i;uvjvbl=AKK>UryH%B=_77Fk@#9&8i2(Ni{JXKD%S4L8oS zvS_Nsnmdm@E`mvOopU%LqFq-fDBN8B(mjVayJ*o8Er(aV>7nR^lb?;v30PME0{|Og zKG)sP?jIBb=@?WGTuIcbSTdaknqI=a?BJVMO-Im}(F9m!JotJ5Q5nPpQ4ly##wf`{ zvL@cJ&bMXuhq@yRg1w>=zEe3t(gJqUu}4-CJI>I$XjhuCGm^AhY@Q&?5B=`fD}n6> zG;|nz=7Ct8DMVy9s_#LIHZuflG$7y6ILQ-S4^mmmL^z!Nah?v_FHG0O!U^z9%71gw zTx|0_lX*{!Y*^H5*b&)6CqZWBTXfCgC`7grS$JVf+=L>jD&l+ruw<^5aOnG|ffm=yNvK|={IWG$8DJT`!gLm7wiZWJ1B%lg;Xql>7N>~vmu0NuUC6j@-Y@?KZ@)xW(sL3@JMdgG@Mf2uk$UO!`-W`s!u|=s6RSUHNrQx{+CcO^v`~GV5B65}# z963d@LQ;CzJvT5H-2ou;XNvq|0MbjoLdFm~A3aC=Ev4|>HG^{4BrAWl6<_mf##|)~ zYyKAuY9+mKCMZ=n>iC}=4FW9Hzu@g_i%LB&mA!A3y>k)3g;~1~U;_fxB4xSvn^Ry! zPUs!Dh0B-TxiWxH7t?|qbR*7H!zG&|sZVMJ_o%#e{}>y}ci*GM_J zKLVfsh}iB7NY5XxmBJCOi)2q37U>P2rbBuL?Q%vnz(2r9eH`rc&C~QdP4x}uaBRK5 z8)qu41e0~2i8ZL3zCFW2M?bjX@{rhP;A-nD>L1~~t^+|eRL$B;11i z#4#&-^ zrOks~yE5qL+H)ztPl}ElNnDp5)mZL{BUT5;1VZ?HxQU`8VLvaPVOfr(c>|!6+$<+I zr6L1Xqk>(*ruguyMjX{O!f_abndPw#-I*^i(R);n^|3z;64=Mkb{iwq)=v8EyAh;h zjrnZ3&(mN9D+^jvaT|P~H)*APXd1VZTOG+C|1T*e7wXl}3E zb_oyb@aXI7?3Ba7Kcbw1tK3NZ4s+hkQAT}8NVc?O%%!nzqeN=m*FF|=u8k=qg!PbH zO+j)y8LdQNNywDzp#k!ZK5NtIkSv0zGGhlccE5mwxu}q6REQf;;@bx35$#|8jEx^ zbDvXVYJrT)E}a;Y`k@7pDztzBu~06iF7z?z!4K%$4y+KW!8TD(Gyv)TRCByNDB6}i zKCi!87u+L=YUqZQ1tp3W zM#}5^pf;%QiT%dy&ma=9%UPPwoeKhe7eLNVq#-i#9rS|o32Guyl%7PvMzmArvour3y!!IdA=yox zgNutP`uoB-(Psj_XYESI(z~|QN|7mj2SSDg#`Ws$l1w4gIjn6D4QgQ5c4@6@*UtxR z{+#3*)b_Q!^L9RQXGc_dUxYT&82UcQ&H-|4D7ZgYu$=zoC5%MHwgN$vZphj`n zF^;Emr4HKDk35KgJ6<3w+YZ(`P$j1j{WHWDvBQDvk;g}7=2GIRG#0A~7L3o%7z`pU{mVDR2qYb|1VY3W39HX-6C(Y?C^YHz$VnQsKYqI)0u<$e}O zACgu*NDFVaR{n`m=#hcGqf8KLB7AIy=5SQAs$TI#94?Ku%;(yJ(X82sG$+lG)~zEmrocBIH#{#FD}```T!sFrEro!R&s|Gpih42o-0sE!bgv zd0YR8FMRCp`CGl19f&aWed7im@s4D(Mr?WZ0<$47?1k0k_%Q=xZ(n)Fjr#Uq96y$L zH_g_2>=I9nf>&PQvw2GwJGL1%Vyq-2RcSw7A<}PX>S-7`KvU|PqAHM<``rtr^A##)$3uJS_G0LA)W~6zNVfz9~tt#8wB4?BI^;R5(|?+UnT_WTGBPZQ8j!w z%4k1QZoP@~53Z0V1Q5*d0CmZ&B9_&al{_=8?cE*MPCjTZ<|~D=y5Bc82ETryls#xh zKAcqRw4St|sN!IWvVGJYrqPrb;ggoOdZ8;$+mf@e?$KqM;uSa;;ySEC)lcG{21u`^ zQOR}C{i{YuPmeCLu*k<0a5=+R9Rzw3%eGrxGOZ8cO5OpgF(N8->KtPVEbxlzbQuIR zp+eM>FFsyG^TvMK(tM)oALY58=h4>LnG zct1&rP;D;Z*1DC?FJHt=`l9)6+QqatAVS?j$$uZE+Su^T_bX&Pz3*V!mT1n>{k&!bmdEvYwZ!)7Y35lp&D6)F{#8t9MuH>Vu@Qo>Yc=hDHng?_$ z`=X!bQW$V5?v-I}SJ&6q7Z?6btIObAF*|F>snGYd)V@#WLpm$Yyc4!BQzwu_Gt&W~ zoq(4WqA=MDxbI(ureS+vAaf4aBD9pMJ)XpQ@wNy1W#TLMXTQDvSjV0JWdbREZ>F=WHWpLl0sU4&2w(XBKl>FmoBI(g|= zU)cu0mC+_fzZ&Vl&!1HecrvSx2fg-|=5mCl>D+iaLt`Ct9Z&3V)xlgkQqVqRaIE&1 zYt7ql)!SsjZ`F1_=R>()9tp40zE6$0ZwsYc9j@6>-{U~w67b_bm&N0B6!|?=J5&10 z`&N}bs`0+6(HsC&13MU8pAdt0aYvs{dQPz6O>yy?9^1L;V7wF&%p%>*{!a_QYs^UJ zaK3EyECLLY<~*c;r&N5ntO1aDvnhkWUc0Y-u8)1Mj&s@{R+zr;n7*05zmVg4MC4%g zN;<1ss30J-JGV8W+s?f6nS`0JfU90DLBHmkjBDNG4Uj~m20o(|#fUf**v&g`x*r0n z;H9ni=h_uk9=WV#P=J3s2jYz$LAzfI{cisE$7Y?}&}V(YB5^2L)^Vw$d?h1+zgUIrG>bMpWYhN(GgbbVVsGoSbg0t*$Mc-KzpZ ze35Lbe&Q?^f?y0ApVU`!$?(fJRn^(rT3XuMYeeuKFoDyki4trSE*OtqSr^M=yg_+< zdQ01hEb~7=Q3~eDv(X}^q*{rcHPj0>tJ^Y8u*@)#@M_>I2C=6W=9*DV=&~`B8OMv( z*c6zU-1aNh+Sg0rT`PC9SWW!;94uhd6loP>1onM+$6- z$Az1EiHGP=hidztiR_}TXTn(pa?=X{I0sAa4vA%B?m~w4>f2p-7D!60n>xQ9R7ZMX z5m{mM@R!2q_g}C|Sr+QW^V)7%;x4b_Pg^P~k^Qos$;?P^rL_vi2*(FVAYmqQ`*o_7DTmMH_)CnX9S}DF zId4n|=s(bFZL7BG=<>EKnM}R`$U&r>L;}a0oX#d-G0;KTJynN6z?9l8xsyg-k7U>U zmy$yv>M$$vuHnDJkwY9btf;wf2wqfI{t30#^}$xI)y0<;1~@qksi0~m%M#4hTa7`R zfMvk_fIH2&>WqT(LMLP<42soo2YE2yF4zvD9m-x9ZAgLcP{|~z;?$ih2^vbBM=u=2 z(yAK>syrMrP%v(Dp1_@rFL$m+xB0!M9W>4+dtN4U#=lpmW2~B>b%H+tn+BTJHfeH1IRE@yOAk9WH@aost91}% zmFH6e>-@1*{b81UDiq!A)f&)nl+Bhgxd2duMx(jK8=+Na?2EjK=|$`qkcuU`H7T^v zw%GC8b;blzw&DHHjHbwH9#lQJP8QU5y9{{4nBQxWCoH*Sa?TTd3t@r(CmXHWi@<#dzdqA`!Uj5i0tlq zPjcIH%Ur!qoZ3AGAUquZj}1sU=dmbAo$|@=%Lc>1^890pN3P!x6DG$+aSG+mNLLP+ zM8olu`+}{U5sRue8QICn$v`xYk{)x0YPC6)5gJT!_VypP0*h1BrX}5oInWPN-!fU3 zBNYgDol9?9UsJQt)1;JCY*<<&_j-6(uAT^&=p2)J47Tu8HF&nLpZs*|U(j3wF;lv% zBX?zs7MIth5L3mG_Os$uE$#T=)nOgx?y2&|6Gk>#4bGHRh#TE`tOYPGCbFoc+#BOT zP6<>5;*9ufLbSLysM%>n>|ghhkwEiR59%Jsv-sZcZFllJA4|^tY!v$L^?h&sKAz0h zOGu0r_*M?+!DbXx+z}c#Tif_o8@%Nh^_W?f-K>m_A{Pp_n&@$Kx|8$%K+z-~o52!ia53xx3DjUdPWUDxf@hr2loO-*2B^oucy%iR9vH76FW0 z^BKR8?1^+l_ryOyY(l}nCd(YKlO9y9m{$g?SlM}nqB`2h$euO?>w4D?-5RrvA3AyM z*>c%@!7Z8&pK1r@uC@%%#*|C&5YztdeJGD<>Ea+lvPjxoTgfmRVYU}$7m-`lrUx&g zik}rD2imUJGo_La_~gRN&{iyGj`%2?!_*vD$BpG(qmj(kOP2+b8D{D_Xd}bQDqNBY zC3sd$mf@dwmk@$$%tbT`h|N@P93rx%u_${=yLL@R!43%L>Av%U;*Oy*38c{xwh5+L zQ(bP?z_87m^vC4X4mbVA)^T+FAHaVDS#!nzq;Yy~m$%>k3u}!Qjj@&(qQ|Fvj0Vk% z3ju4H-nWtZ{Ot`N!}xYxk67q|q?FfSs`CeC$k_Q)$op#cgRn=ppgQPr;2!h(gs>DI zo#>%Lh=Cy!I>gZTR6CV_Ur)*Uo)ll)0vGu?W*oe6KuVzD{vun$=l(t`#U!6dAfFkB zz>UM@YdGE9 z?9Px}eL3zGdZeFGD%hwU91bZ1IQB0>an_t3sf@QexT zBBifxGr8A%L2$5q#UZPa>^RE+VSK36dKQ+i6NY+(fv=tA>tx3i<!Iv(X>n=;HFOTT zZ=TwL0oQ?oB!_4=Ne6|bv)QJ=3)HF}r7n>^K4xE1VJ@j4`>==+cqmDUuK#h=Cmyy7 z7ZB4|&>%^KLhSzBckeN0I{uP?;3sTi8PHFE*7@B_{qQ)R`>%*659`zEbm#4t?O`pn zvwoSG&{fN9Uz5% z!tAZI!e%|&hcVAGi#FuHr>gtAFso5kR#rjfr(to@(72~p>XaF3CLZi~37cYGZhsV|C$d-=SEy!SEEFc*((8~MSG?@(CPQ92g;Wl(Nb{TIb2=*P_l}pEjPp)EA=GEmTTj zwN8{v=f~3cXc=Jy&cw$mpwXYkk0z!nJId!wHW8j5jpI1m8R36AQTD@PIp8`cTB@p> z;8}>TiQijbMA1NLpqT_%Vr(M&aWA-#O*&WwitCc2VtLw>j~B52`6Yi3k&&<^4oiG$ zS7bF8hptYHysG&Og8zvLvr8h;NDGG{$e|KSna?H3L`}`1z=8KfUXBdN^jL`GZLD5R zw|;!UO=xQ8(oSrkrRB)D@h`H#1SVz|M>{s%eOXF#S6`jYu0{OX%G*vImDQa?^@0^A zKf0jJISs(^QoE0~OssM7;z53f>2rvPR`KGnfQvu4`jsu8a=gv#?SH9K_GK?c+;Q!i z$aLoP#bC~RxBVs2=dJF3@E7TvFv}IEs!gXGDeud&b$v>*NLC3gLXiC_krrG>dx5o#dc!z!(THL=!q zp+zLf#=$#K3zHwun})~0WF11<7w+mx>kp^cC?E|^f-Sl_Gcg$Pj`BAR>nK>0%eBgy z^zD(#3qCFC(O#Ln9Dhsm+6O)x(xCd@p9kiV{fk`}8b{N@34~AKdcz>?GcLpm{dirG z4J%5)2b8fFbKa^+ALC)ogCGN@ScG6NIti2h6>dVX_s^gm9zw@-d;6>O36u=p{>qlv zaJYoO-&YIE>00r~ol>V9NSgoe09}25&D<_@>EO$Ad>L(y&-mS92<_8QfV)>`6)(8` z%e(|kH;Q;Mol*p9qM;*yx>XJ$Ha)wu;APE5Kc6LxTs-U#8DRn)vTnOL?8$mF2S~na z=L+2U5}s%J7!}*usEJfdewK{^E>bl;843n2%^y|r&CDkE8iq!}KNt4ErI~k@k|)Tk z+APaaq!i>*c8l~A*yAJ`zRkNET^lZ*6{{H~D$bf-89A4)=bMTB_99Y}^m3y>lmSCS z&R5hN0dZ;t<8e}j132Vpmd1Uj$j!7n434+s(rpdN?A*ttW&hBGT5Vx+A^}JE6+Gpj z7%}q-Gr`1l6WwAET%%tn0Ck6^-d-h5cUQw6Hoio+wWVj}Rid~sEKMmKSgbI7cSf9B z%VRG@(CTgUk0}&Si&aG!UJaU7mYBeSR4Pq z?NvFQhT@#V8AK;0A3>W{Gr1?Ro*7pw_wf5vv=tv8pGPUlW+U(yzo}_Kx-wb3!lcV# zI%|0D!pzt7zvbIa*W>a!k@HnB$zOHR_l$5-mR|d*sd}B`wv4{ zQtk~&uNnzWhB8s=2?=y~c zXz6H^`xc4JJ8i+p1zo~?Q60cPfi?n1j^L$2_9>vpNwKP_xpPI5ZpsJi(jVNX*Ve({ zR_x6uScXER+{av}(5_~x8gEcoX!<=^Zh}Ww*ELr(V^LWtU&e{rIjZv8^a77cD|u>q zqam$Fd4o)?b~#fgE&I3fGN_6|VdN6gvt$<=Wl7Y*e*A9Wfo32PQ7Cg@5he`+ z*n6qut59b{>Z2gy-F_Gnk%O?{;uMbkzb%8ku@0yzK zK*$`7>*BnTk56_`sBxxmA`K<88Yl`Gyn&b3J8-)h6zcpkx^8h%#Y;vm)C=4M*9R-> z*np5ran65`to(~YOEjMzjAmEBYo|0o9zv+s*B?2y1f;KzDC{!{BJ#3`(c=B68UJ_(A^_vIP|IR0{93oKsc z&P|ifS6^vVdW>Y)8=lnYz7i4_-@r2yo0&-1GEX3 zCWXnxFH#+LaF+x%v>~C-d7)m0Pv9nPn~xf}>j32e=6=yTaycg_MaBU~r;-2o6ulHEib zX&r57dH-9?{$UT41ISM9*=Sso0(5{_lB_PnupHzO(qTEOu9t}Yx>D%$I5XxTM>12t zs#KWk+|}n;Ymdv-MtkndX>Rf7$C&E$EcM|flFeN_3Wf%U-}u}e&95m`t7-O82{*R5 z$|B@|Mmq7vbBjbGDi_BAm;HP~(+y2q40f442eFOh7Nn$$-(kiRfm3EkmUlneeys}H zR_T!oAM&~sx`8k73XT+yZ!+%H7<+2rA+LrKcOU%#+oMK$*^P; zGq?knG}gag*4oNWCRDAkQzL#;WBj;>uY}-C!3vg+n}=2HkJ>|R)v}+E??gee^<|^qn;%yW5{iy4iMS0OeiU1Z)k}S%#?H3zsktz-C*(JUE5vb z*F!m5ubRp=%)WZx*$-wrMLr zkn<9y=GE`&gBdHiNxinYRwh~KI!M9*)YZ>qCS``=QQ5|4((nx@IKy)|r~TjaTT<#y zz;WQzxo+M)#uP(!xN7a}YOXmKlj$^4u+?EEg&w)FmlY^YOla9?(sEi2BQ4!h*IVbZ zZ0&4&KBDd73f6x4v9H?}SA^rUvc|z_s)OZo{7bJ)TgM$*<5C2{atMXn6zIQ*vclfL|0a!qho0mT_Si)2asy6f|4Jxszrt8o#MJGA-0V>ZWq zFZ}TEP>0KI&H|Z;AH^xXccemyO+n<~p*MWY(dD-OK2ol6Uj|6n;vJn<)tG8^a=QK^ zOc>t$>}et~)$Q&TV{55r{vNgc$F4^BZ>ZbrdX9V!ZFSYFu5BUts@$5|J{Q)5z|1QCGH+7l!IYa5M}9#7}cIbVigg3PdLm3jKFy zCRF*XkaH%pNQxKw!vJ#(1+^o6o{6$o>T15ojS}c;isyEkI%w$Cp%fpjgMB1vT?oy= zH|%&v9P;W&=VZdp28QB~yiwLHG-jNqr#k>1vefi2k`Ezm}@lZtip z*M6?mI#5)^d28tIE9h?;YyBo;p5uEx_zCZiF5Ui{*3)z<_1{9#PTl>@Ym;jKqeYNf zS~r}^Nru}RJ4RV2XePUe!d3Cl2yoF3GQ&4nX9TEqf(}kiyW1vMP6*0|w|cCFA#x6( zfzjWQjW%l0N|V#Mzck%<$*1Siwa{v_bs1KcMoz9w&5rMvx{MRtaM_1>0@6X!C(Z!B z!_zF?LiQ`0+rs0#i|Dx_lp;p>Js18UD1BU&4?5hZ;XB7WCp69bqr;S5ntOSz^ZHM) zH${G~s+V#_yPbR0=Tgc7lvA7#nO$4DHrH0yO1z+MsiI+91<*?{;Y;-vL;iI*6E?|4 z1PWUEV&9$5_TD7e>2iQ3ao^R~r;z%p%}A+s-hWDX&qi#^2mEcSzY^<==1CLxG3UE` zc73S*|H6|Lvf;~40@W6WtJ^b9V3GB&i6*{_(yVl&Lf4NUqP_v4)G51&}7iS(j(!WYptP|ty|s}q=-fTmL;qV&ec-5BBYnu z1d2frrk#SGYANRMpO$+zmFa+h$1Ra~(NCFku3i-0|3!@HDNMAKE|3G!l=i92&KA^5 zlnm)HkU(OLtHj^Ad4GmZAj2nztLAZHF5na2%9FaIZMdXpI5W|?rp89LrkIdr#!`}we}thhJ_ku)TqwVrC7aD9vo@j z0iz>I$UTK{VLrnl1Q;Sop@EZSCezck)|E*9nn@dri7j+c|D$HsRXa!kQwOncfF3BY zVWTSt*k@)iMgwU>8napqjZ=K}d(#45&CtXU_n|&{fzUl8(35YUJ@uyu^?t&a?&x^S zpCb^vt1Gw2?>(xHzFK@GP{h0?*q4gG_&nD#^!W9;HJd7hkaWE5I5_`^N+?5vj z7b{OjwxhmzHiy)gSE!QBj=$U-BN==VHKnc#V9Zm@LY;)@ak3sWQvEzUeXAA??BGQ=F#wGA{f~ zc9?T~i!vIhZ2$nWDsW^m#P|f1B4&pjU5^B*{O3~&wI-fT_<+}+SVAi($8u|V`~&)U zxE{I*m^w}n1gib6i53k}8~jWU3j9u@P2ZEKdtyRuq#4!SkUVgzpM)Q)U_}{JsK1*Px$r06W;A)!=5TVPs@LpnJm7 zm`l~{ATG1bTt_~TsgzM*U!BLxYW~n4a0yR9DW=fVvfdkP20Vg%nU6+7v4r>SCMmct zMHwq>b$IyjUu<`IM1H;XQ~d%&K`S87B+E8z7|g6MynX6${Q~wAw}#1U{t!e*R2aMy z?;^pnnnSR4orbUP7cpT3(AhoqtFt6fkCT#YkOnA{R37?9qh>w16rq)*8x!W5pARev z(xb;8QF`-{F8W=rbpqJBw}?hnO4%Cg>f$KnH9zQf81^Nc4IW2*tYGYv2C-l)u^%UWMVhA(b%@_#%PRZuHW;y-@*L#oqg_o9BV=5 zX76nLS}ho}2gdtftZlRsO-&7h>ZrM(#_GVR)7sMVFjbY(1JJlrR{xm@EO=akXaS}) zrZ|d|33GX4Ux;eh+7B&_0^fpZEAePx1iT3DX{1QQG zeXo*ZkgYeuOfY@CMZDi;&n^VdBLa(exy>Fi8|TNMDNTA{<%nORZ;4xMDGHgb*21O> z7nF<-`iqZb$P|~VXbG!=ug=xwMLf)b?TSOTu)i}K!IFfv4O2P|wO!$yxa+~1M?C_ZG^nF`+ zX9*7&M5+3!iQ%?!llE^_OSISz;Hx?t!=yqqZZ!Sy`Kq1U5}&_(37iz=vSoQE;b}v$ zC81MmOl<1IJ)C>zs~~U)Ui(GM5u9sB5OXD};79X*>9}7!C#SfU3|-wA{rwFi*^~At zXJX5D>1(qmj7UlKzg@t`YQ;Rc;&2ff^`-X<2a}Wi$q*&b*fUt&9_n4V4Y{Y~-qZwO z&)L-8{dUz^+jSRpVdi!(*^rRJ)7-TYgfMD9a@+eQqXjT3{Oe(v$Z$Uw@0a2TvP zIR?b`q4H2R%+h7plV6-8bd`DcWmO5WG|$=qgieO|8S^8o>eIHG~dqhuzY zE{#lM1<)gOSGdk+EN#JdZ+F;YfN;so`MiKjyI1=MMUR1Ml`Z9mr&U*0P`d=;JK}|+ z#Y(}x#T~1qG5&;L!SAcz9DtKJz&4u>KVn_#Rq>`uA)U0K5{9KjtR|Doz>Cb(L7HX% ze$Cn%AH(0E_V3R&CB>2p86?oU?ek!AFh&J*OnV>yAjAFs zk<_Rh%}{VUwp<}kW%x7y0lqlEWGzMSpW3q6fog3x_qRdE=At68vg`p&i9XAyK(ee> z$F{PY(#6@xtsgxXb$N@|)O&XVP;V%NU&0XGU*%6;>fN9BhF_o*gNkopnt#eot5zU`HhSwIgncGX0;=ARP(nseyl!7wF;^BnX!s zR4z?-^i1#_BE&-ml6Jca{b2Ps`N}hL7U3exd;0j&eFD5()&+Vx6B82kwSr2|u)INL_dbHRb6j4w>AQwd?$F+Fv;wxcPUy`5cM zX*uz{QL7qP#&#d4EahiCBihm+qGpusX5C*nU!_^!0>dn zQ{X&7c4gT}!jiP;hSP@X_?i-hb*kO4YIj)SaWN=#T#7yhgd$`*O>E-)Y*LzwNnyUZ zuN#k-9N_pq3g0ATHz_2D{fj~_w3)w5DCr9MN9&ekOq`d{pvzoATFWkbp@_B~KPdaB z1R7+5$vuIWLJ*H~uk%AgNB1W)3+^~}(RK;{8r$1tJaYoBfb5o|LE@n-@I?IU_}v{H z-+C9WT`S>N*EYp<-#KH=AYH;!zY{YdfETwO?7gKYj#v@H)cei$U(DWQi-E2F{_cam zC#CWm)_77x`4Z)_T^{*3H}v!g6~M)WzPF21B$5~?1BKg&;y77Q)AN~$)j-ts$3-R> z^ghkk@q9R)1EEZ?Da@cFQ=*dfJ^XKiiF@hAe}`M&)5IU5-g?Gt|ISz#=lnj507vbM zN|8-BPn7EQG)PKs9z|)T1gC3B`_$FPqeq<-5z?LV#X}~ri+g{~%@n?N%}B=*EPz-; zNR7m$>X)b;y=l7%HR>*mv9$!A-01Qh16-RKQD|n(=yxWUbe_czSL;a6h*@$% z^Ywy^JvAb*jZhBgmq+mKi$L05>AO1K29Nii{wEX}X3auEj_?j%l~6)geV2U?adri^ zqz@@r+~dEaCP5cC0Z11v54&aR)ZJqE(^edNFyD~~3|kZe1UQ6$;5-jqzj!IyL*HJ5 zVv?udnug~7b2pIkGE*$IEU6}S0P2(11o>bwn#rJqfH9{qsF%g@H>pE}7qC;yrq30A zzjh1i4qkK~{iF2TJCW%mQW3OXDZKa!_*>jZd%x>lvAwtJqDGQ0jDYP!H48cIwp_uPsFS3w!yD|L6a5AwhvZ^2j-KbN=XO5idJd(sq@q8&I<2PVVy zkjiDZQ9L9Vwm(x?B0gh`^Z7BLLb0(d>*Dkfn*2-rW9#?gIg>KlHAO6fhfVglZFGDz zC>IJ(c5jFyI<+t8c5J+=1FbuQ(myB2wVCpM8yJ22e<7>`NGZTn(^KWx@WT4&s~rZUm3$lUoBs*av?z{B$RsvB0n zY0V)Kf+{^n?PT<3dHMML{oQl&m#OW5eTbg5 zX zk*-DLo{qdcmg4f=VFEz$*7?x%5ZCT2nnZ+fhC%^h0r*77pf5KC> zTKSEe)DlS4XP&iK<4GOJ0M0m6E;S{?_KS@zxsd2rek;m5T7q^z4f>Z?3c21L=;alu zi9GN!St&v%XTBJWNiU*Q?$1NIrIbVa*Z5`23W(^`aZj+F|VCiQMb*sZe z61>@?OTUmz+b>2}HfQL~gdvoXBKRmpru#4$a1KU2frP2%3NBd1LMtV;gTNoDPYITLVr!?Ow@QK?!yX^0yY03d(1%UfZQR z4=xrCdykhsvfe`-QZ3?O$ql7F9{i1ZS^P~R&Y?k(VZqM1%}*XamzwG3Jo6NBytuxb z4uhxO>(%3$2wd~yRURJ`a5fE1;sl>RP{KW~cz+NN@BKnof1DqaOpCvS|GQ;e@YFY5 zE=TNCTHq4LeniRARP79{<$Osq>{PG4l)Y^QMkLVDyW%ylxG_GA$<~V&$sD9(r@z(q zrFz7NIA`m26^Ir;4p*5l*l32Jw7Ex2(d5kvS8oP+S8E+fin}T|N@{nEWQL+&EvFbJ z_Dxg5G!|k(g`zl;%?k9JdT6>C;i)D0cE(}7I28yvK*q=szWr~gW1j`2r1_wP&6rQC zm=>FW^IA;#sb_bQOTu;7cug(Dt5y5yp5`<%z9Q)0QUau zFC9%q$tQA-Ic ztwXr&I?C?1dnflJS~m)b5uHJCJqq`9fwh6|e0T6qr*a~?lH!O-#-;;^!OP@c1@F5H zwa0H@eu&Zx)dcPPx||0lMww1e>T2SuCyMjP6SEGSeL0=bdpGuWPeLtL3BCXk(e`hp zCa+KpK=X}67{?ZAMi<6DO4O;GZF)KU0&`kOIXR(?l&xJUm(L268-}lh1F4bKaMU;9 zx7)9O|Nbkz3-<&^`~JBJWp-0@f4tD?Z*8)lnqf@xCK}7-`nfMYXb)(yhNUQ$<=;I% zrn*dh7z0sNZB`bth1_rVhd>~kIZU|MKR5jdpupSk1apt?zrRbswP{ZdvRw>7$^1+0 zpI18jw(hO&r6mo!a;F^Gb5C_5PJrQY9lo~@z>j3f{o~ag0>?aTURVZ53V_poHI^&4b=4Pv?3<7Q@}gbs!6a@LaexUHu=Rk0m=HtMp5AU z+V;VXXtY^YQPcq#O*U00h9Hr(#fhb5$c=U%(nZfGR5;&$QO@VsmTQP#Fd)*NLZMZi z#xe;Un;#AfU>VxZQ9*TcW}~H3Oj&V!Zfv%KmUuEflFD9s_!z)Fs`Cbat?MV(0j0Qm}_cYbps}H z9(*jJ^{)EX=J(j^SvN*#!qWgAiH=eizZ@G$j0=*buhWcFZwitQ0T}fs=Oe6++VH+L z^{}7VP2Vt$F;=Q{Ke%M_>}{?66<7{hxHAmip%7c|c{5+HHVEDw|!SnGO>(LDZlw8ej>T%d{fK z#CbUs6<0n!2a!dRFb^fs=(qHIzS6)6B$4Nyl6P|EWmeh4c>B##)3)Ar2kZY!Scp`6 ziRqfWe$aCv(cX?+%6WiAoamR zn)qC^JJ|40Kq#J>gvscpbR2tYGU)4J4(;$0_jk4MWQ7ZP+{z(!RK*9Mlyp^!{!wTZ zQ3jyVqz>9j(vaA2O>Jj=>U!vd5WhZr2ZV3i8w;0#jXcq%3@WPT zI$=Nfza>D4*g*&FIf4TQh~KrI_3lVnA-Z6p>P+~(Zt*V!M$$;SM-vV$CyJ$`ip!2M zQd52Yw+ooPaCr1Qd5Q5Ut7`VsXg<&O$x0#=-e~Y?boRXBeY-H|v{}kraa5?+>6!YV z-n+Wd0|VC^{nZAP?jyg9gQLZAOFcUJ;r(q^!w^TEzE_${1m8ZwtOH`V78U$)zxN&; zz4+P7=5_#?H;kHs{MSY7eZIBXlts@$Ay|>&S`aiL--Uo2yw`+q%Yjs!?8@{GY{3QW zNbte+r*xcm(agu>OmpKi=%Os^=FCRd^7yF9Y#@(}0#ez2fs|AzBSj#h=gSZ@Tb}pF zUh2_Mz> zvm$4Q>1-h>0uKSY%u6OPAlX@v_K_H238eLmcgE9bp+ie1MUow(ZQ%snj((@q)2}Na zsEo1qqDkNF{m*6@q?nT{4n3Encb2SF4>8u4nM5paj}fz0wN31w8TXpIsG@=y571tc z#+Z@?;1`L4@s^A^8#Z*LakSf%<=ob}|BTxv7FP)dZ;p0Zl{34tlf#n}(;~-9fP#^B z`|Uj3gDI3|Zf85BL1!xMtrb;86gy02l{h$Lsf!gUZ7|A2@AMe8fWr&SoZ@YGzxQ1w zj%jV-8a7Loi85Fp6(=Emgh1F48y0VbP7M*8;RHY59_ErUOXkc7&Fs8*| z4MD@_7e<5|a8YZ*s~hXS-IPBW5R+zP39wzu=mT?9N6Wo)!W4{+Ig5ThcXm?isXcXGjz+? zp!d_;xWlxu`uOJoOq*TO`;2xi#17dmKgcz(c^SyzaKDSEfp+X zG2_xVPyR0*%`IFbWpzYq7n@MCb88J0e~!x<6V)yI<~)@{*k@7&v7*N-&x{6eQzH7VxrqsXr*bRtyePWDvklOHx5WllN=JR$8n>ZN zM`M5ttIrFH*OZGx5TRTS4h$GgRj%~g@86s>Q(bacq?F;v`93m~FuZHi+LFSJJwA=U zI+I<4*Z&lEEy@s{AspsUL`PUKyx#g*3sTu4#0z*wPPh9!T@A!nA-)z7`+jLIQ!R|H z2BbC4o+aJi%lrLK*OE3AzMo`|7kZ^hd;lTQ&)6p@An>M|wygJ;orZMNqXG_Bk{L<4 zxY#)P|C~98BsLJcvYeVIHA)O~TPApvi_;9{(V{>*n9D{cvR{Yb)6^tE5dz_cq?&*W#a3KViFiOT^F&(ZWkNcW3sO7?fmA!Q!Ac@iw5HwbykA9Ja75=%zJjI2feO(Rd_X-Vl?a|Q)4q9TeIj5?s*A0#p)BGZb=4J^yiFH z57y=sJ)1+p!LVf&+i=h-R?e*xYpq*ygtlrbFqr-yRoygQ)G;FfLwd}wDz87Gwq>X zrt%MAZ4|$te+6vQ)aNU6%L%7P?QrFk4o$@ma(QxB)?-?<(RYslEPRuA7a&h$QAy>S z;3VRxW8NU~l-SKK>87+B&rSv$S`oG|Zc>X2e*LR7Qef|HYBHA)WtihloP%$$%g^BZ zQ{Jqg*?7hq!6EB3CB50(n--A}Mt9bSMoo9F3W3KqO?IMQDNC0>t_d5(wj(F&kX5sY zn-ok%O}3FCE=@THkG8>45%l)z6jeGVp`IbyUkn_LL7!KP71x(wTK2nY2x3V-!cb@$ zt)wuy9oVBftBr0d(yZ)*xA+lQ$j_{tihw>Q&}+u{*G^ft+`!Td6AJ1%k_>r6w~3mT zSRNhduR=0=6`B@u48B@j#>*`vW3BoxhS16bgMbeXYmd4Y9`=R@yI`!b2(Yk9f*XDd zUM1_T-#S4dWm8BS-<8sg=S4}#Eb9IJUWT$S&{>3B_`;Q0yF>c&m)0m=z>)ERwUD>3 zrzegO9>X`xwnK0k(YzwR4Am|lvPu+&NPsqd^UbHaZVr)B!T$;@$3l(p2!e{}F9 zj}7073ikHAIFt4A=;*dAnq#%Es~D9CA7vv8KWq>PrvoI<(h|v%gOKetHL0T#z6k!s z%W~G{zrXZB27~z_LDd>B_Q5^a;$12Gj9#QNf#YBVt!CzNqZWiP70N!tFJmWi{N7ti zU&10^#|!Z*`1k`?J$u8n?tXO}RYZ+*DXM4Ui>Wkzl+Z9?tomB{avlJoG7)9W|L0D! z7B(>0M7iBYRoILa^QCVj=xk|7PrvMw{{>tm%hOj?@0nJtOh+)l)*(=y(wHs#YvhW?xl@Dxz- zY6+A4)ms9ajkEu^o&l2pYubofh-5ZBmWX~>;jsUV_k0zAePqRv=Bz6rF-+b0eHfxJ zv=a*QK7vAs5=SYd!zd5G(15;ee3io|@t@ef@P}diG9mIWH(KJLy+a1vRP$GL<5Ws4BkX?!%w3Ga<4d#e`OKO5UL*TP zyqyGihzR^=qyUy@$J1O0J#GG_{QS$elk?+!Z^U+2SBc9?wO>OZDeqHwu<&bLsLOv%nckxJ`uJZUoNz-n2ppC=eQddgLxtJ1kSolyS;X%D ziS36be-G*zsOoN7wXgvcKL!Mg_rWMb9n_CEy^HDCPTR8CI4n{hKrW+r!AI?7<#>VD z**C2ndin;m)eL#`*Wb{vNwM-CffMuqS@Ov20=D9Yhz9-5(J`s0O8+qyB{ME^Iq>ub zWPd$>+%;1;c-}e2pO&QUA5re51DIDx|=4E+aq!sw8 z8@2}kflN~#$!t#GhWyJ4tQ%cMJp@K@I-16V?^m^$kM+qVneRS*1YLL# zdb=c>m!b{pL2M$MN$mFneBg4*<$7G1IEQp*>}BNJ8&B~Scb}JZ(){SEO zC5Pl=-Dcgh>1h~T1oHqV`t`{g4k8$#%i6+}bkmm8c5Vboyx-{z=jJc$98b%Kdb;h0mI-tV7Qs1?4Rj>v1@V|u$3ZpsOUK+7{EpHFg z368uQ6>rR)R&6nFcEejx9=<>*R1$X$+kDC6BJ7n+-I);XY*LYS1sNTLYaId9Rwuvbf9xO4hS|Fe{b3CP%x2O?(B zPDB7|47y)IKD4W=3ZsuDBg!Z~%8{ARiy5K|;*V(m+wl43h(VDSFRfP?P7T(ymL=dg z-q^y7!0n=%lHlVix#e^=h>k|A(2q6tIy z@+xA+Erf&^t7sOz;bwDBidO0taopQKb^3B@>uhcJ zIvU@=X0CaBe3KenXm0Xm19H#U@kP3G-=kH+Q>z@#E(*qTPUl7MW2hQ)adVGAlg}hy z4Z8CU^j&VWqC7oDz7P{Rfom;KVf)g(Md_RDv`-O93s{imPdux_)} z>v=@#Kuq?_taVQ0_6X80cw_> zny`gwl*7Yo8G7~g)`eu@g=4%f?3Clp>@K^~u z`&?_(qu4RAxvAf25YoK4K2-8S-MbV+^;VwITUNv^e&TdKi*kmvu9A=`8x?!X)wNiJ zMu$@UhjC^U{>5#HqNWbK0Ddfc@iC@#yz8$Kks}4Z+a03y5ziKmk3uBGkmeYII|jOW z$*Yfo4yWl?1b7wYcM~!UxoEnWahYiEse_o36Ql+hD3oQ@KM*^I5TUA4O~C&tt1aJ&tYF@2!T+ zd2BpO#e6^XEy~lfU8|zMs+G)g^G<3UJ(V0$uc2GThsxsxZPN2D91l&J;wzo^0zOz$ zMhQC*oaJh|(-H0lr0m6oq;_pr_pHOP>D~h)z&;TvAKq|L&Zmw)3|AwC#0*mw0=;wLclUyq?o{ zKO^jSJx!PyyVVV8ELc@tog?g@X0>roFp8Whc)@?Yo|1TnuazdFFXpU(UTsGo%u%b4 zDBB|fa6;9RNTaTBV1=>#tPNoMq=mQ3q08XRSf~8 z^Dz+Od^dr-qTI}Fo{JzLRbcnqtyxJ|5n{RV#nv&EAg}P2Ey! zaHIj;2ceRx+nY_e&-q9v+(41`z$fd&e|IyH-RGs?&mjNTcGc=X+Eun=W*@%o)FC@G zu3BY3g?ilymEkmb68n#ADHXzxw^Urd?d+Y-w+Zu5J8diXG}b(O27`L?F4xIbiLay|X4PSNPF z>_@_(dew9!J!H&k59ZgbUm4HvjK|JBtHB5V_W{cGq(Hc*M={7H);jw6d6$acx*UPj z{Tzuc^!CEsbvI5wSY5Nz;q};W^L1+F?*8xS`i|Oex@67MSKN-!H(8t!{%*i89#I`o z2@3NV?7vYMgPKJOWWTp^z0P6BP-@--R!xhxg0_|9ZCrEo?({o7E(cJAi;d8*C#1T& zFRMWdJ|=xBz$*T(rBra%yID)pIIKE zgf>$?8iWJJOGcfzHy$g_8;f(6QdrNLR@=}VVJA7%?ylTm%1Q*UT5nNg#d8d`ew&dT zH(xfj)~FG`7}I8h6)cjPMMJ#f`DCAjTOwXD?Bxg|H#&k~3)9u&H?FDE;=c8x{4(C7w!qZ=>HJC-zq_R8y+Gu#-e1-tAhT6;4uT+#=@k zH(po&!;y*==SEJny6+Q}+->R+FPYh_Ns^>aiugQS)Rg>V8cXqE8^Hn}z$6(w8zp)n zp24-C!`7HaYq_^`kxny^N|18m101N}Cilv8i2$lal4wEL>URzS`x`7^M&*$+SDAV^ z&d?}nQ?(I<8)BpRG$ylxuCCmhkR0`WDu_+M!lM`#f1$fY1a9F0;yt$9ptgaE2jPX+ zE*^xG`;dvoLi9`Zu?A8t8`Y;-rt9 z=rPEszXTX*=MMJr!FdSoR7}P^izasF-sWtCqxs3w`~Ut^|GIRx%|>n*?`p*C-qFZE z4tqFe(g?i|P`z|Qd;%s|cXDT!+$a&lKIWyv9MLtuVB75d#cAMM8NGwHL$P$eIUV>2 z&f?}e-P24`*%hkA=B^7=V?nGXZV(HbBBV*0p%2P~Ski4V zxFkE{{7fGbM6N@sRt(yZC6xHn54kxxmX?K#x`F6XAMIusRW@>8G^2MgH&7aFO}^O{ z6xD=d1OM@11sQq~Qp;dj0&Y_wosL2ES@7U{?cj8&+Ctybh1R!rHa0Cr&W*)g zU5+k6Yr}t9R+UVQjEQ%Tr(!4zS>eorcdmJF0=L}z9X_3#=$?*_=b#9#IX+1Ec423K z&|qA#&yjdZ^^@54;9b+xJ*PDVD`a#&>rYFWO+)GTrCkU~mjex?oSPy7aFn?J4hMOc zCg?s56jYL7g&5=_EFt_6@yR$uNHFyD^n`D)Fw?z?f``Kb#?YyfJLO^1E>4nF~qaMvz=+2@zv`^6Ga)2%XMNo_FPgFlO3Fo zrnpmzd4%3?2ExPjPNs8$$=NYwLZK`;%SWtM*n7)=v6}V^9iEZ_eH-A{4MauLHDcGv zx@jsz8P_u;&vNgGrE+1O%>f97o+^K5_9YrNb9tw5}Kg=^O-6x+wm;O)11?4ZOfU5GhKF7hQ5xj%1GBKjHvFMixkG3y zlZjVD&cWZB?W=6ikDNf@hQwqvyx6@mCE4FeudHmqkC1T9kX(6hai__)2VQ)o1ScJe zP!AH%6h$xF*(pqUw)E_(OVd3uw)5HY{&ZvK%wcn==Zs-j2K>Jx6J`CWqEX*8)gGg3 zknoiz{Yu2qTZ-e{p^mh4y|rvkoqYQw=}7EbI@`2U!O_3pH5M60`azBMM(BXgtwaF% zB!#%n(u3|5(U;IpIWx_#<{0_uWr9ztz9(~lLB>>mmc`pUP-w#va)+=zHeTN5Y1E-_ zJp!d^S895<=?BwT=;ZL%14Y4qeUFBz3<4uZMwlp8gu5Z~_wV_k5!i4(QVT9X6>elp zw&>6rJ@>j@ccG8U7GWT!Mf~u1%jd3IUq59kI9%1gR+JpsA4t3>c1sGbHS#T2At5b> z6#Q0*BW8(}%BxV(cfTuCc(D&)yHddC!kPC;wl_3j+aE(Z>~cJbE7Pdu>WUk(Vmzw^ zT^Lyt)pxP zRm(KpDcK>TZ+0$ZO%N*w#$^0yQaH6~a)O10Rd$T8Uprwc=97lFKeOWGecu3&M zjNloSNZNn4+yQYk`yw7L-YY({`iwL@v5#||Z&b($IR#lqL_hX7XdvAJ##f4e5M0+8 z&g$qnfG|}(|Am8Ad!#R(G=+7m-#s71f8~AsMG<=54ZhscBlh2GN5Gz5@O=Eaj1j%e3cuIy zM8?{>9GyD2EUgfShFfBiFF4PG-G;%(KOcH(3CB4?hm{}SW}5CQ)3TjU6US4Pk}AP! z@nk;aO#35BI#ZPGS*?8J9TE12qveFhXO;Z?27mt7Q@B{P8rf;gTVd0gKB8TUeq@CR z*Aa_WtY)}I2+iKA$PjK;8BgFDcnQ4*R1raXEM6(#-&71pF>s4t^R z%X~zQNmy_$4HG3vdZqp=);H6}UI@9_-a&=Qt@#IM86Wv~EIbG7iC6U@%BvJZz zaTmiF0xP#Jj(O41*$*>?ec*7Ti%l3@!_Ee&?DozYw)4bcT@we2Jf2$0wz3R#+JCD> zx1zOa{bgB+0{O19P(FFm+);6Nbvn{Od%E)3mZ`kr@Dr8aYwKJ4!veq4)6OK#m${Rg zl$2C%Yulw%nF`XhowG|ti_k(NcQc%d0Y!IzGVPnlq6yId^JL&csl51Z7=1&i4l>uB z?KkBe_E{CZ;xybd*1nR>obVE|?9ruq0uC7K=ZT+Nb^L5xio~w z6}AJJ;zJ}2fuL;2PQLY5&dy5?2=gDlP>OeUKO^M&^vKxZgjX5PY*gHwaoI#J25^!7 zYNBNiQ!|}T|K|l^FIp)#uLu2-ze9 zyD(DDW}H8r97jI7wFJm1u~`Qci{ql6irAM{8wt2D@YvH3lPE-PzrW;t@yZ}&m~ht^ zltfBgd*fkxbVx%jLrET(+WMqFpe6}Lp~=v}I33$_+Ht9^O_%&*y=}plvxsFb<1)o& z52BiKTLoX;NT8tn$jCY6w(__XmI8Ly8+z*fPB>BZo#6e^uWe8JCvY@+p$)C1xP@~e zX0%N<3gpH->ioK8hU(6n!;Q>^#yh@A_d83U&eh@VZt&de`EZm5O@5n)zqV`)LCO!% zo}+GY@mjgcC1w2~%x1NM~mCXIcyLlF3 zr~a+ItNC)wk!yXnRi#~%zk`Km3GtRV(vGdt5 zQPXqMFXDs^-#-lOw7^1Tr6d1JbDA>f44=x0ND?S8xI^?9)yxA+YPI#`}W;R zeYYd`FrLf%_%Ki57z2Mi-;mEkdEf#p&3qK9t_FY_O--LDYrRxtusSk=bgGq&ZkYD= z_QnCsu@KX{K)>XimgX~;tii8?z+pHD`mK>Ls24#R5{KZ-Fq>1TOP>`pKF~*=Bs75h zRR7oQ;avbI(YS^6lgEye6U~=gh;qyHDYA@<>+v+tqoki>tynRCv2|@xCn<@{?jNJts(v*^rdMz%amai^V(F;m4pLJ zX61(pvAfNZZhPQTuE}ZGAzs*K{Dj|T&Id$9&iGxR$efmA&j(j|*Pua$Go^gWCd8xx zzC?8slalZU2W_o6vq6= z0eYEmB!dXxT!wjIFp1Eps2sdZM%n7<8{BX8vf01%gv#tlnB=!Q(L!tou)XO~GqqZbTp?L7s3 z+XScno4F^tl2(UK;P=?H=m_gCNg6o%!&xm_RdGhbAEE;3MOjj{CS?@w7WPMwOqww0 zk5g}>9#V?Daa25@C=n-+mrfMrqUQOH8?R%JhR`SZyAAF z^^SiH$->5fy-geMh7p{~C?YEV{Nm-ec=DB(vDJ9>t;`tMdh|u!z-TjqWwdi8WkME4 ziS(j?U3#b~E+g8RFK60#{S(11t|DWjH(oNIbEyAHTqCS~LCFE=wuhOI&6#dc?(`wR z{J1)oU(AAKD*|^e!Fln1Z*)c=5&WYV$eQb0<%NuIML;vwn;2j%k&R@g_9`NsBPfuST^1E4LE&XY&6B1~Ra$is>s!kUEkD9G?O}ss)~Z5p8<(&^Rr$s7Zx<>{ad0PUJ%!D0gQ z@FGC~Yf+E_d0?0*8ZtMpvc4PHH(bCl1xZ5m;i_3yqaM!Z|bpW61m1dPoE!#(gZrN*+KCer-(qsw~!*$W%{TvAGX%QBO0yL zD&-d}(&a(vW@%aTLz(cMqOB#QpPQVa$NrSBg>>*!&PNzh!QEkm(Qoa5fCOzkGAY*C zFi$2`9V{9Bf8#W7_su@qi7y%{v?mq4C#oNnGGv+nu||K{%X&Qah7_cMv=TSh#0c>; z$$On-j2xcJqZgPQvHtWFdwDe4%ns7VlnQ+}>O$@|zY4w=thC&i0+&7B(BdEXYNnGG zgg>0w;!GD+$+8f}j6Fj+5f-q?!=IVZ@DeeZDK=AGT3CL6zwhNK?E6}^1uSVhP~(N~ z?P2N+PFFipR>bDrv}*1^OV*d2sRaDgbsEL9$2<3zXH2Vc!522EyKT#7RI3xwD2KSQ znDjPJPJ_-?I0dsKA1i@M9BN8a{w=Ba*^~tP-Ggxqs57b1g0Ooo{_puL@NEG6%BqL0 z`ClcQ;sfP!LCGITIt&KOyrQ@VVd1fYPVnrp>%mzqXf<$4ib2Up4}{2HL!jj@?#xNu zq=q3T#JbdzdQI7??Z$E{mcrv5u!*~LSxdnsY_{QFIJa`Q%H;<_L4kJr^vvg)Ty$Eo z7};Em9BQeCSsEh5;x5bHR5V)|VJdkXx-)l*_57^8&yVjE%j~!UwRyfT=45E=P-F+s zWLke4S5ZdQllzV|uYnL4~MYMN!{$b=J@6DxpEJ`5Q%>>Fe43 z)0NXd$R}nonW3t%pU#t{xUJ@kk!M1Z(d7F$R(RsJB6+={k~R9|n8tHBmSQRf%do;&J=xCKYn))u$_Q?NkvwN0ovPYRd*2iCr)?$cibG4sC35_%yCmwB z@>_+F>F=*W!mmN1lmDV*u)I8@k02ilx*iD2Ds&GjJudutt-SUNZ+pC&76JxwJ8T+5 zy0h^3JYGm6o7$f~AY5}ciM_snXfUEdFOk%_&($EVIjC@-?EY%$|7iIjyN)jtltwVi z2Kw__K0ZEvJ*N6VC8Roo5)T*>ZAoAU5CRsZR9MdlBJmGTrKI*xKyw(w95ngu5VldV z${g=Iy=N6TiXKcNY>~h@1=`hti*bYXAQ_9?kdTe@N~g4?n@CQ}s?>%Z==yeXMd%#D zazbK~5c)em1;jqo%(7#EmR}F0N(EKui{WJx>H1R(N8CAE{TcL=wPA8`m!J!Ur&aW_ zm{9Cx(GWue;p3ElVvo^g1{g2=rI5rmr|8Zsfc2D^ebhxHqw~8Hj6W`|0$7SY1X~J~ zuW{E@83e;((zN|K4}RR8Z~h=>b$yXLojvqgx-7Mt;!L7(=qvy+VLU(Iy*jR^j|m?s zM?yWS)vTSZ)v>i^=6sw*QH&o+Lh;3=Tgf{l;&4waeI`$O!OAF@2&Wr!Lk2?cq+p}U z=>jDr@YtDXYB$-^5c=B4OMZ0>4*6k*7vT@=jp|K1c`Ahx3=F{RQ+@21CM~5n6}lg$ z&u9)!j1DwOUVd}hyvWP+dXK`!}5%2qs7dPVWIh{*OCTVA{j$dQn{?Q zcmtj(id}2rU)ZGGzH6u$G$~~VVqt5tsz{Jpr)KK|?>5ust2SV(diQ-r2;Kfz0dB16 zg8teMp(`*P?Hj`>0(!`77-YxXq!~=aQdjuu%13okC%|!W`LxOWr`{MpQVh5ys7IDW zW=KEsQXTz{Vd7bexEW#*D!m8tzd4*&V_M?~`R|6F8vQSxnzDTtx4#n_GJqJ3KBte>5tijRc@ zfac3sC^DI`)dEKx5G~nNcMIeGCbibLWDEE*(epk5k~!O(nH_9*#|rG^WSz}g=Y3pQ zMy`S1t4))>_r7eJpq{TO#=WC{Gb(-b_D~!9^dWT(R1t zG<`B29)WbZ6=J*Ty8|$CSidi3d#;WhZcgfbDWMfen}| zdjIo3`vsEyBzHL^7y}K9ubEf5^th9fOO=oSpbt61Jmj*p)Fn3>ZezIm=9_O0hWk%` zY~vH3_#}P!*6ZJU?X}nDXIiijl*3HMqavdQnMBe_LCwxGs5S9gC6P?#p3NEYC?_i` zD~+rp5}p;2w9%gJbX(1B8cDI=<1vf{DcRe=TyMlSMpD`AXkF`A5);u#;*v6(kzqT> zNq_AkQd|QWsl#6X+_`gP;OM?ND*MvGAxJpH;~2zbZ1e+hSLM{KII?-9&{^#WgEyk8 zS|!0ql#kVj(iR`GZYm$8BD|x-Ch^whA5@<>;_^3}E{+0F<4W>a*fW5Yq*U_|bK65G zQno%>xwagftZr)I4ZdGl)Nb65`~T2aS(4EYcel1pQIZ8M&maZfV=^kT#dBTQDubh5 zD`OjSd3lD`ktjjXWs=Gvg;a$>y=61a;De`8ciSD^>3Th^)o1`NYasaEv@UTY@mf1g z4+~&~Xw7t`rMC%TT5Cz*M>i}yCbTH}1brY$f1sIYq!BH88oBTmx8L5UO{_Of9$9&g)5b zE`TWLg-c_QR!sSLI1*nR_sz!jnX|PrSVZ1+V*MsIVfaU=HL^h1K{oBy9oS9EB`jcl zQ9d8}@R7H5jf*eAEC<{j95?>yDqHDo;jfdpkryNGDn1d^ z!7-M$%n@glM8p0_bo-=|D*1}(X}S`mCUTi|udlCv?|a|7c;P&47O^>-5F*DX zEz}oJR2;((L-U@O#zHB`PC>S8q*S+W-dvntpxHx9K^0fPk0KR(WnP=!daTqf2{^BqGg2?aLXP>37=sK(?jED3Ss2qDc z+d%%OKX=x*NpV_OJjJlT1Oh0^bQW$^Vdr0=cF9a4=-Fi zuVkx}mXI~ND6g`CO6d;IL#*oU;q#wa&&+Iy11&wcAZKBoMPQ4oRSU%eNqQ5NBN6SD zB<^BP_6PJyZtYOm2?J&=W#-K=_OW&ogpmT8Ph2g@3iK`8Wi8A+TXkK}c_-iNQ?v`}Ahq=@@`a(m98R zDt2I`h_@`xb%F<+NL7Vh>d6D|Gtnt+&SzZ5)$yj1#9+V7esTRZbr2X-&VBBqramXo znUnymmSn@yVnNF+BN%9n6J%15m^UYvHP*4a$k(w)ItucZy*eJ)tM)1UC!wz3RW3{m zpnz>aUi;1yb!8?d!6ODM7buolNeKM?M4HQIK71$+vEG;>E>9+Sf)RZ;VCnP>z)ge)?7OYQ2ACd3C$m z(Yf1SHZ+Zhy*Dh8I8&k!AhvouqmdtLD+L1y4XFI8ov1UJAd)$y>iG{nVdx<8=|A)< zr~~kMe*#LH)|alQ8k#7kt|)6~jUSJX;Z(^h7W9lrwJ`*YN!R(hg#WiRFYL_WY?+44>s53jH0%Go_(V3KK; z$OJ<3a1|udD_d!-Kslg6P$tbMvACz7etLg*o6dnqx_{QUPTv#NBXC!g^|C7aj1nl8-4v;Maw_9XMyV3VDkSnmSaihLJ$c~1 zk!#8BeOR8VjjL6eqINg!mG_f|yLjp+HA6erb_f;R%GQ1x$aGKe?20_LcX&~%QbbkDTJDVRn&hR6tQVh(&R{wa{Q<5kLVLW03eCv*hlcf$JeQc5^Jk%~z_ym|8meYLr{SxIIQkPOf~lUqu*xvKK^otqquQ3?H) zY^!Fo+vK99xZm4{T1<>>w$))BF*~K$;2F@3w$|6igJH_;L3!T~dOZ?0M8}seT}Yz1 zDx>YK{fny?dI$H0gMwQNN+8u#NN;A=8KL<~hC)6uKP2Xf9z}@oke((+xTw^MWlSy{ z_V9>@jkP(&)k#FWK$4D{nFDDcB!g2t85&qYlU z5g6HlY5+=DHvvOlAp*=IM`FT^NzB$VOS>`SlNn&}!kruo8dzi-`f@y&=R~le6HagC zNM0(bWm#(T;;in-H+H;?v!P3AUTk7Fy|G3@7e5iNU7D#G`U&X`Hiw+Cqm(+mxVXE! zOE+yLs?lJC?M##IuF|A!#2AYij+lQScq$VP0u07!ocwOg;bP9InN6;{K`hzFelns^@{OnRVFaz90H0N+X(--H?-taWJKXc6{7FSc*vNOh&tkban$N| z7;i1L%|iULhD+=X4CCUxp)M;Y;Y{T}nG%*$nnC0&nN$w#Qg#JQ9HBy*lZb1rBe8qw zeXfX4$U{d$>JiH3>6}yv-nVRz2zcGJE~$-iD{1&#aULUMkw=LHk*bI^XVIi38qE0_ z8YSvg&e3tJ^l%wq(QHWaWRw_*2<43N9AOIZ=mzNFd~v3-*x#gI?Fy*IA_-)9n<;M0(BOibLJKFad}@h+HD%7tQtFgPy&J};Yv;$|ro&QSq%S^DuP6Gm;C|P>u&EHl45iF-d&p5^^JRE%FcGWk3atSbI(1;N#;Y|(WK#E zp+`eb6(L^nr7wMn=6Ppl>xV!50qG~4LLyE9FbB?|%kx&oEMhyO3y{kz;^M60uxjcb<3udye7vic1`U(9Oty5u3JLBskW_?r zqeIMVdz-t$kZ7SZ$ubSo2)X*DH;~BW7&$HH&Yc?#IHBn7og2MgFS&dP2&IwK0$say z?WbONmTvd?&wu{Pl`BQi(9$3fq|rG;Ny8fkb82P{=w79CRrQsAF5?pxK34Bh7IP$UVPSz5 zeQRq+sBX;aI77=Y_W0uBqQInaHWulku|P&IFV6y{9Cz`PAaQ#Wgz9aaGjfe9WiXPA zD&qxRf#56K1O;K(347zX(9*$STxF?0!9$xwb)l(UYClDqQNG5sgS^y75P;WF$6l6) zo2YU%z<%9<+o@c4-zf>|2k#%j`%uF3!$D3(%*sg=XjafGyH)6YURuN&%mUsE@D=i$ zfyT#Ok)6q>0w>N0K}c_5;&!UCp;|F|t*zn$kEIV#Pwg6FOGVCEpp6Cx`D1CttfWN3 z?;zj%Hx4j@^R-}*!gV{q)H5d4aix4N!6_94xHk{Qm=0p+$Pn@!zi1YK4x~1m^o+f$sNm9D9HR&3RNiNGi*=CcSn9n@-tm5pC!&9eDRb_6= zJGm8K-_M(S#^bX)Jqh=llZhM(WqUGVW76~Hc@0~Dk<&);z7qTzgiXUkP%)eq4w1jsC-pC56_;LbVHiA5#H#?jqd+**oOeqm?+EDc8 zzx#jwjLzIY7?5&OD)Z!%Pm)=C=FFMxjZM1L=H@1yfBxJB;6ZwPfvX?9N47Nmgv{o$ z%xN!^7~;YK$@RcE$%v)veBypC&Ebl zyo`dXS7v~=*unB@KO3Gh11V-q&9CaXeMsc~gqqGLS%Y@bTl*D$u4^27U6ptrUWCb5 zs#&H)30%xx6h=<=$`kQgCoZGJKecxGZpt}r@gRWuM|M57i3fsa+N;2(q*xl#Y;Yn6_Hz~Pj{BYVBM+ZvbiWhyee6;ko+qn-rJJDi=EpJef6@;xTOS+`j=#l` zKv3=O?*WijaU`?q4TgJr+o*UU8|==VTOa@U$BEZBI~_=R;+EqBx!*uJ7NA0I z7>MNOg2Y75E%G+j)>_R@9FbYr;TjumfXb3@eSQ6?-4NKHNUvf4IGg1;cjap& z@%&6{zZwwROd4F5a&#mCVT4hgV!;-i62{6MX_bXDuDG)=@g-u>i*xfd=kv33$}3C& z%xEQp@u-{PrzUGMj}vgYwh`Fs7aU3A?;XpB>fX5 z036qVNdQejxKC-1CT(EmiNNEmMuop!TLNpfiG6Gsy|VO<5_&WNkG5S)Q;B<|3{z>j zHtSQ$V%wHtk;~|6&JKl`^j&&l*~jWn4D?m6Sg_RSsLGaiT8^% zjF1*kN<8NhZWItwBMM_Ao|2err+B^_qzx%{-wgYsSaUN>Elpx8u1(W4rc%Pi5+;-W zw-U0<8m&%umdH;haS50c0nQR|R67`elSgoh*I?bowo)!cnTR;JWZ`Pm2`&=65gHPg zzaWYuQtj~7qb$wJVk8PN)Z$b~hrUJjwyguCy(?CM;UWd8sS}q00|9I9=a_S-pC(u^ zP#JwDE(K|<$hprp;}NK;sTiPr;8Uq#)FVzm+v&0uS&r#x8fkX(-p%>>*{kngV{>{q zRGDi+t2O$3O4v>p;|fO1%F3ArS9;HQO#5E1N5e+!S2^Vdsdw@?xwmS>zaUu&a%I4G zF^x%zMwQdLqzHOTm4We2pSigODQXbyJ_6j1z~t&Q=3+TX9e{rgaf^I9PXTWv&qcZS zk*Y)bb!tFp^4(t<@*v*0wE(}@S^e5s_|_{l9t??ZC(=rGRH~hwohWM&w=XI!-G_+5 z&L)k;!MNzm&l=S);;dgXytXP;r^&U%gWdr%i8fn+#8n3(V$e%Z*|u<|)yT-G+u7SC zGazaw@4ox)<)t%OBiq?nUszZu#-mbl0R%OdVd`jS&(5?-#LUjlGKgIiuWhbhx^xL$ z1I!6UlJFOtpgbMdZv7{bsS8qVpJ$n*hV@x0DnQ9(4!7!50S*?##)xr_AV0f z7t@$!8)(_S$b^!O%E2zMf$HA9J2c_+PiBu4< zM>0+dwn@rnyG4{V&WAdhMaNry?#SXe4*T5it=~6rWNX`cyL9ZAnOtk$E_K&y?U}1cS*sTKYRimtPHLo01<;^y> zi4#ZF;%lqDjV6jU>mmioF8Y0%G*~pcA`wm%p(id2q)BPli2zM{Y3&y0XFt5NwYGM5 zZf=fSIUap*aJcvMQ_m(`e;@Vsds*7Nd-v|_%sk&Ji`uhoV2|CrdV?md-ENBS`j8mA z&e&OcB#7MYtU+U>MWN9)W@cwQv&FdV9rn%Gme!LIKI$KFN=QCtcUwuEEI-)Y%i`pN zJ9oJ3>+pca-!IV3m^CFyv>#hO2xMj@Mig@>R(P=CtqaNd!Hvh^1jCxPe$DYd5!&W9 z@%+X}MKLzpncGcBZ9km>wmLh2-sU!s;ku(cps+gbQuulYF=YX|005RIw#&NSYjH`pR zz^kV;s0qm!NQbF_^VAW36gYNe(wnIry(AL>x8!p6~8IJ#?)Y@ zKG7}=;C)z;-$%i~j+>qS=TlFrCPj}gPw=j*sgd|Ahu)m<`r!(G#LOT6{P@y;gpcFF z@z3N)K;o{}f|Xh`9+7OI_Zu49@ZBn$%b#VhQ)*M8%5=n1ai$ z(H5RZENZerjZ5o7)^{`<3y)_Yt|*pXxDl5bvt7ko`sB&=(m;O8`Zt?CP1VfQJRNiM z4Gx;yc8;_Jr{-2zdk{d5UXP>b`H1ThSxz$(;mjYj=R?_JWIgE7iOiyMT})Ka_|YqZ zo}rNBt%77%YXJkg(^(zN^2*8^A#{?D>L3-$NJXeXXV{`aOI{ADgy%3uY&nP|!=#LY z2D3rtkD829LLLCul<0x<;MG;qq+?Q%Z+>{2rgM3D85P|N3p2z1AqNBG)-Ewm$!tsO z2vnmLb`qkX&QnZBM5TaE48MCRexFo?H|s81)e4-Ko#Dj#0~|jL`QnaeckOIiU3ZIYy1S5oz=Tm~%hAH;7JlnmpY^k{~} ziTNZu3si=4V~m5sN>K8Pk!=~2S0d!z_kKq74a@IkeCT1b-d0W zKC16WoC+iaJrN0IS_OLl-S2*Pb#;~IisUIe#2~T4^Xg0*8^Fcj=m%*a=s9HPq1!c> zs5Gav2N4Ql&V}BZBf_=Fz$$2aptJ5KRMj!Lpj(QEQ(-~!^&q{oz9}F^ufSd z>owwJ3~0NmGcp_{Lss$QD;qE@9T;J_FOc)~>Z`BP`EXS*6aOKffsTHT%8&*I$2~doI59*539G5!mc3cewq6`f(avouC3G4wHMfDL1aKXr5Le;rrBwDl@@?WW8V%g)FxQ;dh(S8mpnL1#Jxqs`CBJRh_>>vce}2g#mLvb@Ft%cXo#~ zGc{c}w9CXfK7rwHr_?idqq@n()Dq~x3iX<*pTLl18HW}TUf(~?l-Qcu1;ozWg?AxcU+fdcCAoRxS%#mg?3luDAh*Z^*~)LeIFiB!D#S;l=8 zs}Z13hex}Tid{w{QXse%F>8>TXBK9<&>q+aF%rd8>R!>t8M*YvQAI2D&~0&XIObWmtGk=2IHIiE|){LqHM;$X3^#w}xb_7G_) z#-o`|yUiM>p*IJ6yWLKMF47`RB0WtfT)Mcov9ZyeX-1p@SCGY;HCnWqbKMT7o{l0k zq)|>ZdgfS3BNiD7syZi`iQh~(LcFWRxP#q+;8^5=9YkuL$!WJg@`de*~Jp}h+$z8LE%GmQ*mgBs-xO%QA zRxVyz-QL;k4~|~?^d}h_Akz7`;L1wbnUN%+wA!hTT1!hyG{ZC@_132SnJIBcb7^hX z$Vezl!b@tL^A}7*qOct0GY;2{hQc~G@Yo%+erQGToO3tVsxa*MIFf_p7jXmL-PM%N z3dfmDc&QjUoS_bsq}kf)O>OgoL><>~-f7p0SX=k0O6j?E#(5Q)l&RZXP_C+o5s~DU z^@SR#vJ(3_fltpPJaLT%}bXq{K=pENhL)Pq^P{~sn4LO;mVaO z-}uHi=*_zyygM^9L!$rbr=R}xCqE?(dz!Pev&2s1+4=EpAGJ~emI;bJks?{qGM)LL zf4IN7P49QMHm|+^{>^Jwc|s~9*r9uuFJGpy&dtpMokU9#FZV*~5BYJ>lRUB!d_h(= zpfV#fVySP^>hP-rFDd?MPo6GTT=M~!>>x$Ig3QkDNFv?}NdztoC`H<)(6(u@1vo?| zi^bdL+$KpJiUjb2!CYhyS|3g1wulWflMINYfC9ZCP_@LbfQ+!U<>l0KiA|+3W8lEn z9@9$Kl`JR3FhdI;A9&Y^^7_m%$Vo2{17bW`t2h(u6NM zR?u{!es#ZN>bEEQIF28oF8$-*>%sApawI;K$59k%n5o6LO4`Xo4?VQDcK6j+UnOmA zb#)cp-Vg+a%tHePC1qEneS&KM&Yr{`>4IdVl2W+5y!`s>uY>!e%gFrveB?@SnO`Hk z6I%dhx;R-c^liH(y?GPvXL$Se?RVdOmu~*%n{Oua35}NI5Sl0=>OxZX3t#xc=AGMI zTje-UDT9V7=&kf9stZ4SR7Wwp7N-<4cttTyVlK}k^@58`l9bc7kGO{o*`@`zL_Qji zt3*U~X}G>OYBBQelE}8UxD;4f?J9q4vLC=Fb;w3*co-8@ z9Eps!Ui{bsDb-ayO4kgioa_ea&xu?k1i6XJj-$sPGK9(d@4x@UAKq%UXg*Wm<9WdbpSdA6pG zi$8d3tRySc(lOKeH3Xe^&xwCAv_FvB|6;kVR%L&ta0m09GzP z7@*mHJh3!w{?2#4L+1dQFQh1`L>;i9B3c;=+(~C8)fEkL(4iL$0RY`$#6EmFA9JXe zEV5xMDEh>vXz&*Fj3F{)C*+#&dxDn|Kae6ug}5T(O>=5UmYN8wB4R*HxV~`{PD-T z&6uY2+O=yWTxeV*6yAI9J-`BSW>B2SOk%M(vWj3Gop$~D^_kgD8Q?pF&wHX4<;iJk z_EeZdSk@6ptO8Lxld-wa`N1o;gWpZ3PMsPKdBQ-han=wr7@NsA*Fujlm;evM zkX%#!5odhtuI zS}k~K;pf_AmT6~ZgLT7Yqe3C&4!=zPeEb>q%k-id4e*d(EyWiDUtJvT$9kbp%7dGF zgle)%Jd~{yKb$mx{b`W{A@aAITFU9`ob+K81plX=B0K{2GI8AR{0GNR;*nrqVWmk5 zavD`pl6W2$LvCL#X;F&{r%-j1rg1sukcVZ#Wjkp2&A*mniryoW8 z`@3`+2>`lUN2-XCrijQ7r}ZNFxu}(6364diLJ4BC%^M^o3HHX|hGi5w4Lv*4 zNa>#CC?89w#Ke}}HrSL>hze#2YdL_cu0|HnMaEX<#TYe*no*#&`J99Kruse(hO&*#5Sc>Jr~efC#bc8km9GN%_MvM%69*gh_1k;a6+rJfmM)XQr)SH zLzp(mh4z_LXcOhfjL-Rv$`zMc!dl`7&_&Emj|TlH)}%&Xx;($Tvring(`oJOY{khV zTtdrdjt0YCl2)xaO;U~_NK%}(9I)l!+EOSFUW!&ztz9;4DXi zTy2nBKZ3EJ^RR7>f(pls_mIB8bMnfx6BQ9>bQ;JW*(p2-C4tSV$VI=8U>LBA;i;#d zx_b5M!G3>hbN%6mJ6pn zkmbNILZd#m80|Gc7I{@E)PDTT_?ZtFQ4I@ZU0M>ljDT~-4o~*2BFjLtck&2{pm{Me zlPabOqE+C@mo8oEG}(A0qlg$TZKP4Zhsxnd)mDmQ9a5A_8;zUxl4;qedyhtg#l=P1 zwFd`>Bq&>LPLU;Bu7_rNj@!_Lz-sbU9+H%#WPf=ZmhX%1KAu^L(IwJc41oTC9TvK* zV&r}UAHo?4AyKi@wzB*rq-`j#B#FUDO`T~{PrFt9gO+{*{T)fFl4r1tk5w|Zvz$v) z6A8bya7Pi%QtX6_w>Pi{$9>KyhECsEWV3UAcDB`M?DeI9U9!`;j9hAGNV_0XC+n9n z)vD^K#}&EbUVr8CLq|sky2!ipbJ7u7q{DE;M#F%4JIR`Y8@$Esl$%#@JEh%i&fe4Y<&@@jyC=>|Ed>d1x}&mgFc?)Hn$<>+(Xf$2E>J0A!yGCRE=e{EK>WNgMu&R9 znb7_siN3aemp&n>f91-R_6#>i?J*+t{#$RoMZ0uiVS!}WyYIiJm@OI;#6akR^o;P@ zsvvsi_@mWFX$;|}3XLKoX&dl%+};2H5CBO;K~y|KT}lV325BK90R*bxN{plqN{eq# z*ZVWhWUlz98R-Y;nT!d>6E+#(F7EyP=4Wqjb8i=hk^ja5>8$V%#tNh-eTPu?Mm#-i6aZ- zng7IFzw%))vG)-fUY+%I;Qj&mVT1JP@R)GPOIZOjLEe4$UAo|DIpAh;J$i$z0cDUA z#m^-*?Xj{b%AS(Z`og7#!b0Qg+`D&=UULq!tn=iP zPd@+Br)d&~`ItE5klT}t4y7Xc!w)~?E>n_dGE__o<=%f0K{#bXp*6cGX0PP;{@D6d|I6!W}Y;g{akljRlzRsdNB5HIK4QBO|KFa`-xW=B9})~xmM2}!$STLIuyTr zD( zPtp4iuHU+S`}Pli_`|>c>%SiKNAvUZFTC)=qmMpH+>dh^VWxwf?|rFgJ>(sTl@tL9ONeB##y))mR=sdI z>A2+q8iTM~Jp9o~)x#%$@Kfb0%AB^7Nx;sHd$p6`t!Pjwsg8f65q|WM2DsB|(of`}s&Rx82bnA< z9uuA>_Y<#N9Y5dOjp2uAI`AV8D5W29!ijhM8`-x%dJHZ}>hJKH4~_?iKa!2jHTp+e z;^5$5IO;RRUNstzd-L;*5Cc@9d^952-^$WLM~R?!kkXkKd9%fZL&T-o&>fH9r(t)a z;!-{+m%^WQ%Agp;n;IsH%OEnToI36`b>a)2wIQ>SbSzS!jeypYfT0_aqOgB-cz1mx zO0)KU^URqux9{AfM<7}C*b^Un_2skl+bi$9$9`F^710Smi&aAZZm-`Vu{YnDfr;*2 ziQx58QsXh11h7X98DG&z#EG+DE9uXRX0|g4n`2q0%dwHM)F_g6$f7qpWn7_)FVw!OcG~%)HoV2} zfaKFC;d0eNa|vSB--n4oBr+#7oj>=}w18 zku>9;7E_c<$oUX;N@{rl4W$Krmn ztiJo@5IPf7IbFai8S;qIjuA+o0-x&IQ*h0%ZLe(&X>C*3l=2`MpmWW>WICrI_Z^y$zIqBZ(Gm_B1`M>^< z=BFIzjioB98Ge$BmBt&Jbhdx~E$V^ZL zrW!f$r0i~QZ_~ynR7Y%a2QAt&TuTW}r=>E@CMi$R^=r4tSp9JA?e5&{|N6iE?`O}RojG%Mb91wM z>huR6d@wZSD{p>3n`Ny2GGXYfM03K<%Eb%x?CpjmIX5y+Dv{))+wWZcpZ@3ng{Ga1 zx?lU%|Bk!RuW!8Z`WyM^xYcwVP{@%$u1piK{mX55!Q7dR;J#?sC$Y(=4G`IfnpGQC62mdYB* z>V;%?cl*x&$KIR3TXt0S!c}`X^PO+szCF+B3}g<3Aw-BsK!!&U0fUMLP##7m9|R$Q z!1v@6ML_t8e2@SEWL6-6NJ0PunY%+mI_adl(@EdH-F@fb%x4ev)=*Wu&bi$o0rBZ4 z+jzNs?ml~0t*Tn{`mf0eICwzAW~W)NSNlq36am!dHI*vM^+Pi+<+aF%xxR8`>!yvv z1N~r7!+sOS7G)n9F??ku3)QJsrlyWAFE4WDv#v$(grCz`6$Ja2VC^nQSuSBfkse{X zlX0*HN?Rm2s{}ufoXECIG+~?w6o5r*lVxkW9T|xD$e3+To&x2tggFEG?kPB))_f%d z35mFSzDQI%fhCSGZ;bdKq5*rD?4uYTE5(B^=%i3n37LZW5mL5#-WU0tY$s`>z7$V) zUh?7>`h}5^q2X_T^IKC>Q?S_%9XeF-gRNV)p8xD8?bxw{$5N?OaKI_g1$SDziCEA9 zHNyjnVrUcSSF6t~S7GNbEzHf&&+p#78&5&hf}dWq(eJCi!3uVcz=iOT2f%CzMlR7t zBSSZ#uK_#3!|uhHCnny=6toK551^w7Y{rYhXVfkvOx9uqa+C}wo+hcGq9FZ8FqX2= z?U9XuaI)F$K9}YZg6JyB4ectT@9_Km|+DeDrbZXhc~n9MZR6-Ly%Kp1;i@v#u5%7gu$ zR%*KmjE|Lzx>stlogev8RtMI%aR*BG4t66@zDAO^h~}h1(RpFC8D1qsq4#tn08_BQ zfEOVxSHePy1(x`auqU-VPqQTl5U{cm7COHcyS8g4X_~vZ6^4H^LVZ2 zm_O%o1!VDrlFF&4+*w!n3>KmV8*-vnMDZpatRrcv88o6PRw|$vEiNt!QX<)v2%m%2 zixs)`>gLUxxm^?J0q_f0^4Kfb#LA?T{(;5GohE!(&J}tHq4^-m=9thmQpeS8j*VVy z0{OsCxV);_ti$iEB;p!rOsb4=sKve_vN@Gn^PY*rrK-LNtainJ0!@*e2(ihI6hiMv z$&pWZ7kn2c4#PnO-xO2QVs$0&+23Oab(1ZnRA`e7)%U=+Zd4{czc$TUuy$>6{V175 zaXA&%mzg&~Pc|S69$x}_N6wYQL`)~4#f%My=Vv&#sbalcuZ~Bx;V;%B$*c@Hr6Wpj}t1y6y2G?UGk4T9wK3*oef}NLg-q9 z_w)9cFa_8|8yy`zdi3a#BS(Naz}c_PO(W%trGzXWVPeaeaE>oR-$Ibf4Gs>%LF3Xy zVH_VgBrhv=wHabEixOmn%EA#Qw`FN*3AP_B6EH@`^bQM|7vC~fwt>lP?&?VCSPuUe z#I4=5_N22;Y9mPYth43AXyicrBlFnH9V|D5p~~eqtlO~f@R6aRp)^;Ro0}6lHxJrAt5&OcHHl-@dtRw_*D1RgH?yX>}#rAZXRCwuf{Rz}?@nFAiK zoG24N1T1{+SpYw$ADo$or7QIZ&&i&3kA}7|txd&TN_$D@BY8ptSbs%j;rAYUn6+$;pQfnIM37J~$-reb z#4Ctfc#n2EHq!Gb@8_$R2#wZ%Xr zpGL&2q*?-2VG-9RN%DaYhF;X^v|>z59VlZRg&*d~ajVz}1VJ)7 zGRSG7Y}rmtO@V32?H}Otg{6hT8tSs;zP{CK*1*F{eWj(^(ivx;1+SQzoq6b?he~0d zQen}mktv=_KPdTLIrWOwCL#*Kh>{pipe*Hz)LV{#R~6UHQ0a(I2h5AeZ^{n-5OubE z8>K`NH=7jNN>g|cavF^77ILbE;j4i4W8|{|HCXalHBxObLJ{JZ;seABI8`rYLkLS{ z@L(s3;-4fI5o>yIsFJF9W`0#~qu&4k5CBO;K~yGc!9P>Q_=*9jeUXZowX=f4iE~_I zDYy#9!$=7>CiM%X#B&p1Mdc-uF=++vf8tuCWTZKtn-R0WEuq|IV)Q>FFSW-rBVB~GjXd6TUgYH7XJ96UkPlE2m>OQIQHgy^tzS|R6 zfFR1bFb|7d%#)v8`;vqO_Mq%ItMG|#u__!)BPBCqSm`?OOsz43(*$@WwQ_|hH-5Kdb$uA^itH6nu;DA_hcr7Z!cJ4~r|9bOyZs-%b+I2?r(ql+XDS`?b6^7yPtx*?)I!G zZqRAA0_>rRj&va5+STI}Zb{>I#{}?osF0KB6n2jch`exKA|_;N;uw6q@FWX_=7t6A zByp<~Z``~UZmZUtQKIt2vb&i%Asno9V1s>>`be=X-7}dg<;-?94k-E^(=ibH_xJ+L zTM-9-45CXpSl`yVpg$aQ0gjlGz&OZC>O8@Y-leR_q@YJ)}>PHwS=^sP9 z_Sssk;YCwxF1QeJeDnGH_wK#xCqI=job*sOYfDF`mjjC3x3=eC$peUk?9!8!N zEU~Y(D8$*SRyk^C9e;FF=F?(8I2t7`NkCPTF;wUGgHtE@XCj;;j z5Hv!$N2$lT!3oE%QqAf`xl#;s{^_Tm4tE|n@a@}fxoPY69eeidfd>Ic626B4IttYp zAYI8W31_8o)*RI-=JL}=k0ErWRG}Xfa`|?%MODKw?ze$KDgnhP=-k{4308C(!h6m+ z=PbrETf1%?IOojNG`b8DD(9i@?)54rt^>b?x5IHm`t5<3-egsQVhr_jRYzo z&AP;dJ1ZMrS|G@Vl$-o{xdxCZP5$Z2UsAao)=n4E0e$AVPu{w1 z{ibzW#>dA82Zu2qHOB82bBL~leQBl21wI@MuZ`&ZYsQA}x#ynp5Tcyid*_||_wS!R zau^Q#G8K;XS4x-_0%u{<&c%gkjHu(HB{1od^azqbX|N2kO;Qwya8TGP$n*ImnzQ#& z$kamV$uh`=o&y46e;TLf@sWFlae9hg41&zx$1Cf8m(GhVbq6&Pbt}vg z@$s#!exMO9bb24bN(UTHP8C~#UGY0RLW9rgV87u3OZhBdLcY}L9@t!iV7KV&)J-0d zP(06aLVT2G&%RRa09you#KeXgeSLlKC&p6UvSoX%wgkJ2Z_ou|C%D)rB8;DlKh%QB z2^+Yy%FH~F=?JEcact%5iU30~lEPA_)k!`LYGuaH&oD2KcPVyNcm&pMV#VZIqCY2; z%#w?6tzuoshQ||Bc$8Kg5c0K4!Z)lk!u*dkk9ggv13SJ98uW@`((WdLAm~9?3b!R= zOgkpm!77c#LJqdfAePnz6cdJ#=R6(k5d`?+trU)r)#Q8R>(M{T`hEVrUj2&<<`?0gk!_5jG0)qfKec-@>q>}*G$mI|* zqTXyj?s1PB8XCgh?vx1akph}TF&Lkqea=!&5eTsD+fE_`OFuOo0;^T*=({vGix|$b ziuRJvei}S!Z0K^>guUiXN;=Z*0gNY}EAD`uO->#L1!C>mwZarIux~g=zU@GEofaFB zQ`bxoS? zZSV^aT%e^d8O0$as1FpAK^JJS#du&R9koKhgo4EBu1=DSYUC0fthO#^jv?5mc?P8n z29K5AgCo3`U@!}GafF;9wWP5}T{)CembP8!W-G!tRif409w)TWW}D7RuoSkxTWM!r zm%)tLt;Kx~@HxgyEgbi!GRQQJ^`$owXlTY~%;2J61n1rD=W01dk4&u(o1fy0jf__* zENwL$*$O|m{lt<^8PfR%91Dy+IEkER!9AHPF=(Wun|rm2$*0+k6Ysa z3lUD0CXbL3FEU6H17V`C|*R;ADZ-t5*Zvwr(AL;DH0T+;R($ad_1*BhBERlwDyc8oeGNJY;bR zYla!^0vIZzeAx((G@ufKP;KF#j32qMu!OZKJ`5lo91NfO)ThD`hKICi6}Wgus)$Y) zQVj7Xn@!%arb3t~W5~ih$Thdz$y#fQ$HQ?s3uvDeOs#+wu+TxOyA8Ex0+N`4Mek1# z|E#cT)ha9N6H3e$WK<{G|CX^J!Od4G8zo6`H}-jh6B839>?*(hg5P*1JZ)_47I=QE z)?q++ILm&H8n!1{NI4}Usdfyzbn>AGfApgtJ$&>bP;w3*IIu7`H#C3{10|X%P#!cK z*dZXHDg@uHA_Y`!)?3U}*>G}XqGr6lfkbjC!!$`8XfdXYWMQNMM1A4FkM*pMds!ip zI0(}28#xg`IOd$o(tCu3eoN9dV9OG1B|^_&R*D|`>THjhoFg2Y*SpjBGT~)xoF&76 zZD0HxQ^6B{6729!XKwZCwLksoPf@LK>1aH>@X61}D7jSJ%&b{dc2Y09+fk-NNEbr4I}vKZ<=Wjv z==r89KaL55)qHw&)aYC0i5!%b#cKBBVaNnXJ63R60U7iGR8Clj52}Jh`EtIPM$mlDiCoP zV0#!mvk~KbqRKnkKMapdI#F$D8SEU@sQJYrweZy?YIe&~e_bvEMxHS~z7BXmu~;yL z+aij{%%;PN|M|UjN+`pzddlQ4C}m3IkWm1S;%W zOQ)9dxV!Nezg%t7D#1!=*grUB_)j(`+S1lMH`^UBXO@4M zjSY=TSm#Ew)2RC@&3mHY%b1((MiH1J(nr^4j03{va~Ld*z+#I%qk*{wFc>HNAyeD# zQit<*WjL?2fnECWnMzH>i64TcpLkxdOfNBUA^M7j^z+yZ#!y*GJ~FOTzzU$j{yst= zZ?;-uX=&lkJ9qu=AN(##IykL~Y_uaYPOSZ7*9^`DvuAV(62YG5lcX^}Kg$f9JuK3A z?tEe*l%$PG6A8LR3AH>D)mlVQ`Ch49sMZ$Xy(siy3LGXUC_8NPcwVVNjQa zB3Zqdr^0b*yInbf#MF7(1R3UpLBLfZ*(SG}pKPQoB~lx@(i#kWyEGCAbEt$DV6;(& zepoCOD@2Ecioe@rSEH6KWrwII*eeS3$ob?Y$r0KGIUd`oiaM=Uty&C&fignqg?`#@ zRZBr36iJXqX{+vI8CML3D+xp54AgX?Q?HE<^#64KeM9BK{c|(z`Pq>|P#GNreI{OR zh`w^UP{<+HVh7^{^`)Xf12`WRfY4stEc&XAh$u;j;WnzOAdCeR$Begz(Ni+UFf}dV zM!&>4vwR=L9e81Q7+EDGVK&dWPlVyt?%wto;-TA>V-JYC=UukbV-EH34da33953%U^yO2p}Ge>kxm0%jL|@*%v+3TS-Pu zGRcTy%G{+BfQ78%Ek2{}ledUgGf(JsDdm*4lgt$xQoA6fY|#xC9s)Z`C^aR-48gW1 zi$Kmqw&-vbY;A(CClcmCM0y$n4|y!kepRvn01yC4L_t)#s{K$jY4c(3Ll}`TqD-6) z2Y4y|12+Ow3SxdBcW+J=uXrjtw06?tiryrk3`$|5EQyN-!W%$Pt0$sZj#2|7Nnim9 zJFp^nen*7_W)cbGi*a2N|97wdZU*Fk^($Drb}e~B@d({}@7>GG%c$Qpo1F4g%yGnT z5w1$5f?a$&bJ)&4(iq6NgY$*^@4tU>ad~WPY>=)e zsSSp1t9j(ek#+0O1=%+{I}2ajvVH@|n{&=NXV