juzhengz

/

LoRI-D_code_llama3_rank_32

like 0

This PR significantly enhances the model card for tomg-group-umd/LoRI-D_code_llama3_rank_32 by:

• Adding the apache-2.0 license to the metadata for clarity and proper attribution.
• Expanding the tags to improve discoverability, including lora, peft, fine-tuning, language-model, and specific application domains like code-generation, natural-language-understanding, mathematical-reasoning, safety-alignment, and continual-learning.
• Updating the paper link to the official Hugging Face Papers page (LoRI: Reducing Cross-Task Interference in Multi-Task Low-Rank Adaptation).
• Populating the "Model Details", "Model Sources", and "Uses" sections with comprehensive information from the paper's abstract and the GitHub repository.
• Including a runnable Python code example to demonstrate quick inference using the transformers and peft libraries.
• Adding the official image from the GitHub repository to visually represent the LoRI method.
• Detailing "Training Details" and "Evaluation" based on the provided context, including hyperparameters from adapter_config.json.
• Adding the BibTeX citation for the paper.

These changes make the model card much more informative, user-friendly, and discoverable on the Hugging Face Hub.