trl-lib/math_shepherd download history

trl-lib/math_shepherd is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 2,630 times (139 in the last 7 days), and 66,521 times in total. It ranks #9,235 among datasets by monthly downloads.

Math-Shepherd Dataset Summary The Math-Shepherd dataset is a processed version of Math-Shepherd dataset, designed to train models using the TRL library for stepwise supervision tasks. It provides step-by-step solutions to mathematical problems, enabling models to learn and veri

Models trained on math_shepherd

9 models list it as training data.

• trl-lib/Qwen2-0.5B-Reward-Math-Sheperd 32 downloads in 30 days
• hzy/Qwen2.5-Math-7B-Instruct-PRM-Modified-math_shepherd 25 downloads in 30 days
• qgallouedec/Qwen2-0.5B-Reward-Math-Sheperd 21 downloads in 30 days
• plaguss/Llama-3.1-8B-Math-Shepherd-PRM-0.2 20 downloads in 30 days
• plaguss/Qwen2.5-0.5B-Math-Shepherd-PRM-0.2 17 downloads in 30 days
• plaguss/Mistral-7B-v0.1-Math-Shepherd-PRM-0.2 17 downloads in 30 days
• plaguss/Qwen2.5-0.5B-Math-Shepherd-PRM-0.1 16 downloads in 30 days
• qgallouedec/Qwen2-0.5B-Reward-Math-Sheperd-KN-fix-cast 11 downloads in 30 days
• plaguss/Mistral-7B-v0.1-Math-Shepherd-PRM-0.1 10 downloads in 30 days

Open trl-lib/math_shepherd on Hugging Face

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