HangGuo

/

Llama2-7B-QuaRot-OBR-GPTQ-W4A4KV4S50

like 0

This PR adds a comprehensive model card for the OBR-quantized Llama-2-7B model, based on the paper Optimal Brain Restoration for Joint Quantization and Sparsification of LLMs.

The model card now includes:

• A clear title and links to the paper and GitHub repository.
• The abstract and highlights from the paper and GitHub README.
• Essential metadata including license: apache-2.0, library_name: transformers, and pipeline_tag: text-generation. This ensures proper categorization and discoverability on the Hugging Face Hub and enables the "how to use" button for transformers integration.
• Instructions to refer to the GitHub repository for detailed usage examples, respecting the guideline against fabricating code snippets.

Please review these additions.