ngocbh

/

TrimKV-Qwen3-14B-Math

like 0

Hi! I'm Niels from the community science team at Hugging Face.

I've opened this PR to improve the model card for this repository. Specifically, I've:

• Added the text-generation pipeline tag to the metadata to improve discoverability on the Hub.
• Added a link to the original research paper: Make Each Token Count: Towards Improving Long-Context Performance with KV Cache Eviction.
• Formatted the authors' information and linked the official GitHub repository.

This helps users understand the context and technical foundations of the model.