RLHFlow/Deepseek-PRM-Data download history

RLHFlow/Deepseek-PRM-Data is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 118 times (16 in the last 7 days), and 2,881 times in total. It ranks #101,224 among datasets by monthly downloads.

See https://github.com/RLHFlow/RLHF-Reward-Modeling/tree/main/math-rm for more data information.

Models trained on Deepseek-PRM-Data

1 models list it as training data.

• yami2333/qwen2.5-1.5b-grpo-infer 15 downloads in 30 days

Open RLHFlow/Deepseek-PRM-Data on Hugging Face

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