ruipeterpan

/

Qwen2.5-14B-Instruct_EAGLE3_UltraChat

like 0

Hi! I'm Niels from the community science team at Hugging Face. I've opened this PR to enhance your model card's metadata and documentation:

• Added pipeline_tag: text-generation to improve model discoverability.
• Added library_name: vllm as the README provides explicit instructions for using the model with vLLM.
• Linked the model card to the corresponding paper on Hugging Face: Fail Fast, Win Big: Rethinking the Drafting Strategy in Speculative Decoding via Diffusion LLMs.
• Included a link to the official GitHub repository.

These changes help users better understand and use your artifact!