The TMLR-Group-HF/Co-rewarding-II-Llama-3.2-3B-Instruct-MATH galaxy

1 models are built on TMLR-Group-HF/Co-rewarding-II-Llama-3.2-3B-Instruct-MATH: 1 quantized, 0 fine-tuned, 0 adapters and 0 merges. Together they were downloaded 227 times in the last 30 days.

Most downloaded direct derivatives

• mradermacher/Co-rewarding-II-Llama-3.2-3B-Instruct-MATH-GGUF (quantized), 219 downloads in 30 days

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.