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

3 models are built on TMLR-Group-HF/Co-rewarding-I-Llama-3.2-3B-Instruct-MATH: 3 quantized, 0 fine-tuned, 0 adapters and 0 merges. Together they were downloaded 2,233 times in the last 30 days.

Most downloaded direct derivatives

• mradermacher/CoReward-Llama-3.2-3B-Instruct-i1-GGUF (quantized), 1.3K downloads in 30 days
• mradermacher/CoReward-Llama-3.2-3B-Instruct-GGUF (quantized), 501 downloads in 30 days
• mradermacher/Co-rewarding-I-Llama-3.2-3B-Instruct-MATH-GGUF (quantized), 413 downloads in 30 days

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