W-61/llama-3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.4-s_star-0.2-20260426-185938 download history
W-61/llama-3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.4-s_star-0.2-20260426-185938 is an 8.0B-parameter text generation model by W-61. In the last 30 days it was downloaded 16 times (10 in the last 7 days), and 71 times in total.
It ranks #506,609 on the Hub by monthly downloads and #168,344 among text generation models.
It has 0 likes.
It is a fine-tune of W-61/llama-3-8b-base-sft-ultrachat-8xh200.
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.