jackf857/llama-3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-q_t-0.45-s_star-0.4-eta-4-margin-log download history
jackf857/llama-3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-q_t-0.45-s_star-0.4-eta-4-margin-log is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 14 times (8 in the last 7 days), and 111 times in total. It ranks #471,210 among datasets by monthly downloads.
jackf857/llama-3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-q_t-0.45-s_star-0.4-eta-4-margin-log Per-step margin summary statistics exported from a New-DPO training run. Source Run Model repo id: jackf857/llama-3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-q_t-0.45-s_star-0.4
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.