W-61/llama-3-8b-base-margin-dpo-4xh100-real-margin download history

W-61/llama-3-8b-base-margin-dpo-4xh100-real-margin is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 7 times (2 in the last 7 days), and 92 times in total. It ranks #677,853 among datasets by monthly downloads.

W-61/llama-3-8b-base-margin-dpo-4xh100-real-margin Per-step margin summary statistics exported from a margin-DPO training run. Source Run Model repo id: W-61/llama-3-8b-base-margin-dpo-4xh100-real Base model: princeton-nlp/Llama-3-Base-8B-SFT Run name: llama-3-8b-base-margin-d

Open W-61/llama-3-8b-base-margin-dpo-4xh100-real-margin on Hugging Face

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