Download model.onnx_data

[kozistr]

What does this PR do?

Fixes #341

• log warning message instead of throwing an error or panic when failing to download the model.onnx_data file because I guess it is optional.

• The below error is out of topic. it failed to download the model.onnx_data due to the SSL issue in my environment (Windows 10, WSL2). maybe it's an issue with my env or cdn-lfs.huggingface.co, or okay with other environments.

2024-07-13T11:13:34.821780Z  INFO download_artifacts: text_embeddings_backend: backends/src/lib.rs:384: Downloading `onnx/model.onnx_data`
2024-07-13T11:14:36.250951Z  WARN download_artifacts: text_embeddings_backend: backends/src/lib.rs:388: Could not download `onnx/model.onnx_data`: request error: request or response body error: error reading a body from connection: error:0A000119:SSL routines:ssl3_get_record:decryption failed or bad record mac:../ssl/record/ssl3_record.c:613:

• when i manually download and run, it works.

2024-07-13T11:48:51.692055Z  INFO text_embeddings_router: router/src/main.rs:175: Args { model_id: "./mul*********-**-**rge", revision: None, tokenization_workers: None, dtype: None, pooling: None, max_concurrent_requests: 512, max_batch_tokens: 16384, max_batch_requests: None, max_client_batch_size: 32, auto_truncate: false, default_prompt_name: None, default_prompt: None, hf_api_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, otlp_endpoint: None, otlp_service_name: "text-embeddings-inference.server", cors_allow_origin: None }
2024-07-13T11:48:52.190830Z  INFO text_embeddings_router: router/src/lib.rs:199: Maximum number of tokens per request: 512
2024-07-13T11:48:52.193407Z  INFO text_embeddings_core::tokenization: core/src/tokenization.rs:28: Starting 4 tokenization workers
2024-07-13T11:48:53.218580Z  INFO text_embeddings_router: router/src/lib.rs:241: Starting model backend
2024-07-13T11:49:21.728148Z  WARN text_embeddings_router: router/src/lib.rs:267: Backend does not support a batch size > 8
2024-07-13T11:49:21.728179Z  WARN text_embeddings_router: router/src/lib.rs:268: forcing `max_batch_requests=8`
2024-07-13T11:49:21.739675Z  INFO text_embeddings_router::http::server: router/src/http/server.rs:1778: Starting HTTP server: 0.0.0.0:8080
2024-07-13T11:49:21.739704Z  INFO text_embeddings_router::http::server: router/src/http/server.rs:1779: Ready
2024-07-13T11:49:35.807165Z  INFO embed{total_time="77.204302ms" tokenization_time="193.7µs" queue_time="333.2µs" inference_time="76.557102ms"}: text_embeddings_router::http::server: router/src/http/server.rs:706: 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,
  Pull Request section?
• 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, and
  here are tips on formatting docstrings.
• Did you write any new necessary tests?

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.

@OlivierDehaene OR @Narsil

[OlivierDehaene]

Thanks!

[freinold]

Thanks for the quick fix @kozistr!