yizhilll/demo_rejection_sampling_QA_phi-2_deberta-v3-large-v2_temp0.2 download history

yizhilll/demo_rejection_sampling_QA_phi-2_deberta-v3-large-v2_temp0.2 is a text generation dataset on the Hugging Face Hub. In the last 30 days it was downloaded 12 times (3 in the last 7 days), and 523 times in total. It ranks #515,540 among datasets by monthly downloads.

This is a demo constructed dataset for alignment/preference learning. With paritially handcrafted questions (prompts), the answers are genreated by the phi-2 model with temperature 0.2 and the answers are scores select by the deberta-large-v2. The dataset containing questions and the selected answer

Open yizhilll/demo_rejection_sampling_QA_phi-2_deberta-v3-large-v2_temp0.2 on Hugging Face

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