JayHyeon/Qwen_0.5-ultrainteract_DPO_5e-7-1ep_0.5bdpo_lambda download history

JayHyeon/Qwen_0.5-ultrainteract_DPO_5e-7-1ep_0.5bdpo_lambda is a 630M-parameter text generation model by JayHyeon. In the last 30 days it was downloaded 6 times (3 in the last 7 days), and 30 times in total.

It ranks #1,134,659 on the Hub by monthly downloads and #386,917 among text generation models.

It has 0 likes.

It is a fine-tune of JayHyeon/Qwen2.5-0.5B_ultrainteract_sft_2e-5_1ep.

Open JayHyeon/Qwen_0.5-ultrainteract_DPO_5e-7-1ep_0.5bdpo_lambda on Hugging Face

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