mzhaoshuai/Llama-3.3-70B-Inst-awq_ultrafeedback_1in3 download history

mzhaoshuai/Llama-3.3-70B-Inst-awq_ultrafeedback_1in3 is a text generation dataset on the Hugging Face Hub. In the last 30 days it was downloaded 28 times (6 in the last 7 days), and 544 times in total. It ranks #289,747 among datasets by monthly downloads.

Generated Reference Answers for Language Model Alignment This dataset contains responses generated for the research presented in the paper Learning from Reference Answers: Versatile Language Model Alignment without Binary Human Preference Data. The paper introduces RefAlign, a versatile R

Models trained on Llama-3.3-70B-Inst-awq_ultrafeedback_1in3

3 models list it as training data.

• mzhaoshuai/Mistral-7B-Instruct-v0.2-ref-simpo 39 downloads in 30 days
• mzhaoshuai/Mistral-7B-Instruct-v0.2-refalign 14 downloads in 30 days
• mzhaoshuai/Llama-3-8B-Instruct-refalign 13 downloads in 30 days

Open mzhaoshuai/Llama-3.3-70B-Inst-awq_ultrafeedback_1in3 on Hugging Face

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