Support StaticEmbedding model

[kozistr]

What does this PR do?

Close #731

Looks like, for StaticEmbedding models, only the 0_StaticEmbedding/ directory exists (containing both model weights and tokenizer). I've added fallback logic to load from there when root files are missing. (But, I believe that there might be a better way to handle this)

Additionally, I've opened the PR, adding the config.json file to the root directory, which is essential for working with TEI.

Log

./target/release/text-embeddings-router --model-id ../static-similarity-mrl-multilingual-v1 --pooling mean --port 8080 --dtype float32 --auto-truncate --max-batch-tokens 512
2025-12-29T14:37:17.280465Z  INFO text_embeddings_router: router/src/main.rs:205: Args { model_id: "../******-**********-***-***********l-v1", revision: None, tokenization_workers: None, dtype: Some(Float32), pooling: Some(Mean), max_concurrent_requests: 512, max_batch_tokens: 512, max_batch_requests: None, max_client_batch_size: 32, auto_truncate: true, default_prompt_name: None, default_prompt: None, dense_path: None, hf_api_token: None, hf_token: None, hostname: "0.0.0.0", port: 8080, uds_path: "/tmp/text-embeddings-inference-server", huggingface_hub_cache: None, payload_limit: 2000000, api_key: None, json_output: false, disable_spans: false, otlp_endpoint: None, otlp_service_name: "text-embeddings-inference.server", prometheus_port: 9000, cors_allow_origin: None }
2025-12-29T14:37:17.288338Z  WARN text_embeddings_router: router/src/lib.rs:143: tokenizer.json not found in root. Trying 0_StaticEmbedding/.
2025-12-29T14:37:17.398815Z  WARN text_embeddings_router: router/src/lib.rs:206: Could not find a Sentence Transformers config
2025-12-29T14:37:17.398846Z  INFO text_embeddings_router: router/src/lib.rs:231: Maximum number of tokens per request: 512
2025-12-29T14:37:17.400838Z  INFO text_embeddings_core::tokenization: core/src/tokenization.rs:38: Starting 7 tokenization workers
2025-12-29T14:37:17.400957Z  INFO text_embeddings_router: router/src/lib.rs:281: Starting model backend
2025-12-29T14:37:17.410927Z  INFO text_embeddings_backend_candle: backends/candle/src/lib.rs:315: Starting StaticEmbedding model on Cpu
2025-12-29T14:37:19.293286Z  INFO text_embeddings_router: router/src/lib.rs:299: Warming up model
2025-12-29T14:37:19.342559Z  WARN text_embeddings_router: router/src/lib.rs:308: Backend does not support a batch size > 4
2025-12-29T14:37:19.342593Z  WARN text_embeddings_router: router/src/lib.rs:309: forcing `max_batch_requests=4`
2025-12-29T14:37:19.344004Z  INFO text_embeddings_router::http::server: router/src/http/server.rs:1852: Starting HTTP server: 0.0.0.0:8080
2025-12-29T14:37:19.344044Z  INFO text_embeddings_router::http::server: router/src/http/server.rs:1853: Ready
2025-12-29T14:39:43.209327Z  INFO embed{total_time="1.153233ms" tokenization_time="303.529µs" queue_time="448.98µs" inference_time="284.735µs"}: text_embeddings_router::http::server: router/src/http/server.rs:733: Success

Before submitting

• This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
• Did you read the contributor guideline?
• Was this discussed/approved via a GitHub issue or the forum? Please add a link to it if that's the case.
• Did you make sure to update the documentation with your changes? Here are the documentation guidelines.
• Did you write any new necessary tests? If applicable, did you include or update the insta snapshots?

Who can review?

Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.

@alvarobartt