jackf857/llama-3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.43-s_star-0.4-margin download history
jackf857/llama-3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.43-s_star-0.4-margin is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 6 times (4 in the last 7 days), and 98 times in total. It ranks #725,697 among datasets by monthly downloads.
jackf857/llama-3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.43-s_star-0.4-margin Per-step margin summary statistics exported from a New-DPO training run. Source Run Model repo id: jackf857/llama-3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.43-s_star-0.4 Bas
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.