TMLR-Group-HF/Co-rewarding-I-Qwen3-8B-Base-MATH download history

TMLR-Group-HF/Co-rewarding-I-Qwen3-8B-Base-MATH is an 8.2B-parameter text generation model by TMLR-Group-HF. In the last 30 days it was downloaded 29 times (14 in the last 7 days), and 348 times in total.

It ranks #320,759 on the Hub by monthly downloads and #88,219 among text generation models.

It has 1 likes.

It is a fine-tune of Qwen/Qwen3-8B.

4 models build on Co-rewarding-I-Qwen3-8B-Base-MATH: 4 quantized, 0 fine-tuned, 0 adapters and 0 merges. Together with the original they were downloaded 4,245 times in the last 30 days. See the Co-rewarding-I-Qwen3-8B-Base-MATH galaxy.

Most downloaded derivatives

• mradermacher/Co-rewarding-I-Qwen3-8B-Base-MATH-i1-GGUF (quantized), 2K downloads in 30 days
• mradermacher/CoReward-Qwen3-8B-Base-i1-GGUF (quantized), 1.3K downloads in 30 days
• mradermacher/Co-rewarding-I-Qwen3-8B-Base-MATH-GGUF (quantized), 602 downloads in 30 days
• mradermacher/CoReward-Qwen3-8B-Base-GGUF (quantized), 298 downloads in 30 days

Open TMLR-Group-HF/Co-rewarding-I-Qwen3-8B-Base-MATH on Hugging Face