siqi00/mistral_ultrafeedback_unhelpful_chatprompt_0.7_1.0_50_320 download history

siqi00/mistral_ultrafeedback_unhelpful_chatprompt_0.7_1.0_50_320 is a text generation dataset on the Hugging Face Hub. In the last 30 days it was downloaded 29 times (14 in the last 7 days), and 1,045 times in total. It ranks #281,348 among datasets by monthly downloads.

This dataset is used in the paper Discriminative Finetuning of Generative Large Language Models without Reward Models and Preference Data. It contains paired examples of "real" conversation turns and multiple generated alternatives. The goal is to train a model to discriminate between high-quality

Models trained on mistral_ultrafeedback_unhelpful_chatprompt_0.7_1.0_50_320

3 models list it as training data.

• mradermacher/Mistral-7B-DFT-GGUF 490 downloads in 30 days
• siqi00/Mistral-7B-DFT 28 downloads in 30 days
• siqi00/Mistral-7B-DFT2 20 downloads in 30 days

Open siqi00/mistral_ultrafeedback_unhelpful_chatprompt_0.7_1.0_50_320 on Hugging Face

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