plaguss/prm_800k_trl download history

plaguss/prm_800k_trl is a token classification dataset on the Hugging Face Hub. In the last 30 days it was downloaded 31 times (5 in the last 7 days), and 1,028 times in total. It ranks #266,938 among datasets by monthly downloads.

Dataset description This dataset is a version of tasksource/PRM800K prepared to fine tune a PRM model using TRL. To replicate the dataset creation, go to main.py script in the files directory. Following the guide to the data at openai/prm800k repository, it contains for each prompt, the l

Models trained on prm_800k_trl

3 models list it as training data.

• plaguss/Qwen2.5-Math-7B-PRM-0.1 22 downloads in 30 days
• plaguss/Qwen2.5-Math-1.5B-Instruct-PRM-0.1 20 downloads in 30 days
• plaguss/Qwen2.5-Math-7B-Instruct-PRM-0.1 13 downloads in 30 days

Open plaguss/prm_800k_trl on Hugging Face

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