The TMLR-Group-HF/Co-rewarding-II-Qwen3-4B-Base-DAPO14k galaxy

1 models are built on TMLR-Group-HF/Co-rewarding-II-Qwen3-4B-Base-DAPO14k: 1 quantized, 0 fine-tuned, 0 adapters and 0 merges. Together they were downloaded 515 times in the last 30 days.

Most downloaded direct derivatives

• mradermacher/Co-rewarding-II-Qwen3-4B-Base-DAPO14k-GGUF (quantized), 499 downloads in 30 days

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