Support Request: Add `voyage-4-nano` Model Integration (Qwen3 Architecture)

Nobody has claimed this yet.

Hello Team,

I would like to request support for integrating the new **`voyage-4-nano`** model into the repository/service.

The model appears to be lightweight and optimized for text embeddings, which would be highly beneficial for use cases requiring low-latency and cost-effective embedding generation, such as semantic search, retrieval, and RAG-based applications.

**Request Details:**
Model Link: https://huggingface.co/voyageai/voyage-4-nano
* Please add support for `voyage-4-nano` in the model configuration/interface.
* If applicable, provide example usage in:

* Python
* API / SDK
* Any relevant framework integrations (e.g., LangChain, TEI, or similar)
* Clarify any recommended settings (batch size, dimensions, latency expectations, etc.).

**Use Case (Optional):**
We intend to use this model for:

* Document retrieval
* Semantic search
* Embedding-based ranking in production systems

Please let me know if any additional details are needed from my side.

Thanks in advance for your support!

### Open source status & huggingface transformers.

- [x] The model implementation is available on transformers
- [x] The model weights are available on huggingface-hub
- [x] I verified that the model is currently not running in the latest version `pip install infinity_emb[all] --upgrade`
- [ ] I made the authors of the model aware that I want to use it with infinity_emb & check if they are aware of the issue.

Start by inspecting the repository's model configuration or interface and the current infinity_emb support path for Hugging Face transformer models. Confirm how model names and Qwen3-based architectures are handled, then check the latest installation and relevant serving examples; done means voyage-4-nano is recognized and usable for embedding generation with documented settings or examples where applicable.

Written by the indexing model from the issue text.