jusjinuk

/

Llama-2-7b-hf-4bit-SqueezeLLM

like 0

This PR significantly enhances the model card for the GuidedQuant model.

Key improvements include:

• Corrected License: Updated the license from llama2 to mit, reflecting the explicit license declared in the project's GitHub repository.
• Enhanced Metadata: Added pipeline_tag: text-generation and library_name: transformers to improve model discoverability on the Hugging Face Hub and integrate with the Transformers inference API. Also added tags: quantization for better categorization.
• Comprehensive Content:
  • Provided a detailed overview of the GuidedQuant approach based on the paper's abstract.
  • Added clear links to the paper (GuidedQuant: Large Language Model Quantization via Exploiting End Loss Guidance), the project page (https://jusjinuk.me/blog/guidedquant/), and the GitHub repository (https://github.com/snu-mllab/GuidedQuant).
  • Integrated a runnable Python code snippet for quick model usage, sourced directly from the project's GitHub.
  • Included sections for overview, inference speed-up, acknowledgements, and proper citation information, making the model card a more complete resource.

These updates ensure users have comprehensive information to understand, find, and effectively use the model.