yrdu

/

S3-CoT-Qwen2.5-7B-Instruct

like 1

Hi! I'm Niels, part of the community science team at Hugging Face.

I've opened this PR to improve the discoverability and usability of your model. Specifically, I have:

• Added the text-generation pipeline tag.
• Added the transformers library name to enable the automated code snippet on the Hub.
• Linked the model to its base model (DeepSeek-R1-Distill-Qwen-7B).
• Linked the two associated research papers ("S3-CoT" and "Meta-Cognitive Analysis") and the official GitHub repository.
• Included a sample usage section using the inference template provided in your documentation.

These changes help users find your work more easily and understand how to run the model to reproduce your results. Let me know if you have any questions!