HerrHruby

/

RCT-4B

Like 0

This PR adds a comprehensive model card for the RCT-4B model, which implements the Reasoning Cache (RC) algorithm.

Key improvements include:

• Added pipeline_tag: text-generation for better discoverability.
• Added library_name: transformers to enable the automated transformers code snippet, as the model architecture is compatible.
• Included relevant tags such as reasoning, extrapolation, rl, and qwen.
• Provided a clear model description based on the paper abstract.
• Linked to the official research paper: Reasoning Cache: Continual Improvement Over Long Horizons via Short-Horizon RL.
• Added a link to the official GitHub repository: IanYHWu/rc.
• Included a usage section explaining the need for RC-decoding logic, referencing vLLM for inference and verl for training, and clarifying transformers compatibility for loading.
• Added a BibTeX citation.

This enhanced model card provides essential information for users and improves the model's integration and discoverability on the Hugging Face Hub.