Artanic30/NoisyGRPO-3B download history
Artanic30/NoisyGRPO-3B is a 3.8B-parameter reinforcement learning model by Artanic30. In the last 30 days it was downloaded 16 times (4 in the last 7 days), and 99 times in total.
It ranks #505,788 on the Hub by monthly downloads and #10,318 among reinforcement learning models.
It has 1 likes.
It is a fine-tune of Qwen/Qwen2.5-VL-3B-Instruct.
2 models build on NoisyGRPO-3B: 2 quantized, 0 fine-tuned, 0 adapters and 0 merges. Together with the original they were downloaded 1,263 times in the last 30 days. See the NoisyGRPO-3B galaxy.
Most downloaded derivatives
- mradermacher/NoisyGRPO-3B-i1-GGUF (quantized), 843 downloads in 30 days
- mradermacher/NoisyGRPO-3B-GGUF (quantized), 404 downloads in 30 days
Open Artanic30/NoisyGRPO-3B on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.