W-61/llama-3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-s_star-0.4-eta-0.1-q_t-0.5 download history
W-61/llama-3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-s_star-0.4-eta-0.1-q_t-0.5 is an 8.0B-parameter text generation model by W-61. In the last 30 days it was downloaded 11 times (4 in the last 7 days), and 565 times in total.
It ranks #739,005 on the Hub by monthly downloads and #282,195 among text generation models.
It has 0 likes.
It is a fine-tune of W-61/llama-3-8b-base-sft-hh-harmless-4xh200.
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.