logan7000/cogrpo-n3-randompeer-qwen25-3b-x-llama32-3b-x-qwen3-1p7b-math345-groupC-qwen3-end download history
logan7000/cogrpo-n3-randompeer-qwen25-3b-x-llama32-3b-x-qwen3-1p7b-math345-groupC-qwen3-end is a 1.7B-parameter reinforcement learning model by logan7000. In the last 30 days it was downloaded 16 times (7 in the last 7 days), and 39 times in total.
It ranks #506,609 on the Hub by monthly downloads and #10,224 among reinforcement learning models.
It has 0 likes.
It is a fine-tune of Qwen/Qwen3-1.7B-Base.
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.