Adding missing head. prefix in the weight name in ModernBertClassificationHead

[kozistr]

What does this PR do?

Adding the missing head. prefix in the key name of the weight in the ModernBertClassificationhead. and adding the test case.

text-embeddings-router --model-id ../gte-reranker-modernbert-base/ --pooling cls --port 8080 --dtype float32 --auto-truncate
2025-04-18T06:51:43.264617Z  INFO text_embeddings_router: router/src/main.rs:185: Args { model_id: "../gte-********-**********-*ase/", revision: None, tokenization_workers: None, dtype: Some(Float32), pooling: Some(Cls), max_concurrent_requests: 512, max_batch_tokens: 16384, max_batch_requests: None, max_client_batch_size: 32, auto_truncate: true, default_prompt_name: None, default_prompt: 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", cors_allow_origin: None }
2025-04-18T06:51:43.264729Z  WARN text_embeddings_router: router/src/lib.rs:372: `--pooling` arg is set but model is a classifier. Ignoring `--pooling` arg.
2025-04-18T06:51:43.338940Z  WARN text_embeddings_router: router/src/lib.rs:188: Could not find a Sentence Transformers config
2025-04-18T06:51:43.338978Z  INFO text_embeddings_router: router/src/lib.rs:192: Maximum number of tokens per request: 8192
2025-04-18T06:51:43.339103Z  INFO text_embeddings_core::tokenization: core/src/tokenization.rs:38: Starting 8 tokenization workers
2025-04-18T06:51:43.400860Z  INFO text_embeddings_router: router/src/lib.rs:234: Starting model backend
2025-04-18T06:51:43.401443Z  INFO text_embeddings_backend_candle: backends/candle/src/lib.rs:281: Starting ModernBert model on Cpu
2025-04-18T06:51:43.629142Z  WARN text_embeddings_router: router/src/lib.rs:262: Backend does not support a batch size > 4
2025-04-18T06:51:43.629167Z  WARN text_embeddings_router: router/src/lib.rs:263: forcing `max_batch_requests=4`
2025-04-18T06:51:43.630357Z  INFO text_embeddings_router::http::server: router/src/http/server.rs:1795: Starting HTTP server: 0.0.0.0:8080
2025-04-18T06:51:43.630387Z  INFO text_embeddings_router::http::server: router/src/http/server.rs:1796: Ready

Fixes #590

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.

@Narsil @alvarobartt @michaelfeil

[Narsil]

LGTM !