nanzhang

/

QuantLRM-R1-Qwen-32B-3-bit

like 0

Hi! I'm Niels from the Hugging Face community science team. I've opened this PR to enhance the model card with additional metadata and content improvements:

• Pipeline Tag: Added text-generation to ensure the model is correctly categorized as a Large Language/Reasoning Model.
• Library Name: Added transformers as the config.json indicates compatibility with the Transformers library, which enables the "Use in Transformers" code snippet.
• Base Model: Explicitly linked to deepseek-ai/DeepSeek-R1-Distill-Qwen-32B to improve transparency and discoverability.
• Additional Tags: Added reasoning to highlight the model's focus, and arxiv:2602.02581 to link it to its paper on the Hugging Face Papers page.
• Content Structure: Streamlined the "Model Details" section for better readability and added the "Acknowledgement" section from the GitHub repository for completeness.
• Cleanup: Removed the "Model Card Author" and "Model Card Contact" sections as they are typically not included in Hugging Face model cards.

These updates help users find and utilize your work more effectively. Let me know if you have any questions!