Hugging Face's logo

OPEA
/
DeepSeek-R1-int2-mixed-sym-inc

Safetensors
deepseek_v3
custom_code
2-bit
auto-round
Model card Files
xet
Community
1

Improve model card: add pipeline tag, library name, update license, and paper reference

#1
by nielsr HF Staff - opened
base: refs/heads/main
←
from: refs/pr/1
Discussion Files changed
+18
-7
nielsr

This PR enhances the model card for the quantized DeepSeek-R1 model by the AutoRound algorithm.

It addresses the following:

  • Added pipeline_tag: The text-generation pipeline tag is added to the metadata, improving discoverability on the Hugging Face Hub.
  • Added library_name: The transformers library is added as library_name to the metadata, enabling the automated "how to use" widget on the model page, as supported by the provided sample code and project documentation.
  • Updated license: The license metadata is updated to apache-2.0, aligning with the license of the original deepseek-ai/DeepSeek-R1 model and the intel/auto-round project.
  • Updated Paper Reference: The model card content and the "Cite" section are updated to correctly reference the latest paper, "SignRoundV2: Closing the Performance Gap in Extremely Low-Bit Post-Training Quantization for LLMs".
  • Prominent GitHub Link: A direct link to the AutoRound GitHub repository is added near the beginning of the model card for easy access.

These changes significantly improve the model card's clarity, accuracy, and usability for the Hugging Face community.

 Improve model card: add pipeline tag, library name, update license, and paper reference8212f088
Ready to merge
This branch is ready to get merged automatically.

Sign up or log in to comment