TMLR-Group-HF

/

GT-Llama-3.2-3B-Instruct-DAPO14k

like 0

Follow

TMLR Group 17

This PR enhances the model card for the Llama-3.2-3B-Instruct model by:

• Adding pipeline_tag: text-generation for improved discoverability on the Hugging Face Hub.
• Adding library_name: transformers to enable the automated "How to use" widget, as evidenced by transformers_version in the model's config files and the LlamaForCausalLM architecture.
• Linking directly to the associated paper: Co-rewarding: Stable Self-supervised RL for Eliciting Reasoning in Large Language Models.

A sample usage section has not been added as no specific inference code for this fine-tuned model using the transformers library was found in the provided GitHub README, adhering to the contribution guidelines.