McGill-NLP/stereoset download history
McGill-NLP/stereoset is a text classification dataset on the Hugging Face Hub. In the last 30 days it was downloaded 8,089 times (2,113 in the last 7 days), and 104,339 times in total. It ranks #5,055 among datasets by monthly downloads.
Dataset Card for StereoSet Dataset Summary StereoSet is a dataset that measures stereotype bias in language models. StereoSet consists of 17,000 sentences that measures model preferences across gender, race, religion, and profession. Supported Tasks and Lead
Models trained on stereoset
7 models list it as training data.
- ufal/DAMA-7B 16 downloads in 30 days
- ufal/DAMA-65B 16 downloads in 30 days
- ufal/DAMA-33B 11 downloads in 30 days
- davidschulte/ESM_McGill-NLP__stereoset_intersentence 10 downloads in 30 days
- ufal/DAMA-13B 6 downloads in 30 days
- AymanKhan/bias-model-stereoset 5 downloads in 30 days
- davidschulte/ESM_McGill-NLP__stereoset_intrasentence 5 downloads in 30 days
Open McGill-NLP/stereoset on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.