ruipeterpan

/

Qwen2.5-32B-Instruct_EAGLE3_UltraChat

like 0

This PR improves the model card by:

1. Adding the text-generation pipeline tag to the metadata.
2. Adding vllm as the library_name since the model card provides specific instructions for use with vLLM.
3. Adding a direct link to the research paper Fail Fast, Win Big: Rethinking the Drafting Strategy in Speculative Decoding via Diffusion LLMs.
4. Adding the BibTeX citation and official GitHub repository link.