The TMLR-Group-HF/Co-rewarding-I-Qwen2.5-3B-MATH galaxy

2 models are built on TMLR-Group-HF/Co-rewarding-I-Qwen2.5-3B-MATH: 2 quantized, 0 fine-tuned, 0 adapters and 0 merges. Together they were downloaded 544 times in the last 30 days.

Most downloaded direct derivatives

• mradermacher/CoReward-Qwen2.5-3B-GGUF (quantized), 333 downloads in 30 days
• mradermacher/Co-rewarding-I-Qwen2.5-3B-MATH-GGUF (quantized), 188 downloads in 30 days

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