weqweasdas/preference_dataset_mixture2_and_safe_pku download history
weqweasdas/preference_dataset_mixture2_and_safe_pku is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 497 times (109 in the last 7 days), and 4,929 times in total. It ranks #46,168 among datasets by monthly downloads.
Reward Model Overview This is the data mixture used for the reward model weqweasdas/RM-Mistral-7B, trained with the script https://github.com/WeiXiongUST/RLHF-Reward-Modeling . Also see a short blog for the training details (data mixture, parameters...): https://www.notion.so/Reward
Models trained on preference_dataset_mixture2_and_safe_pku
3 models list it as training data.
- Ray2333/GRM-Gemma-2B-sftreg 6.3K downloads in 30 days
- Ray2333/GRM-Gemma2-2B-sftreg 142 downloads in 30 days
- hamishivi/mistral_tess2_rm 16 downloads in 30 days
Open weqweasdas/preference_dataset_mixture2_and_safe_pku on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.