jescy525/archon-sft-v1-dpo download history

jescy525/archon-sft-v1-dpo is a text generation dataset on the Hugging Face Hub. In the last 30 days it was downloaded 11 times (1 in the last 7 days), and 126 times in total. It ranks #541,719 among datasets by monthly downloads.

archon-sft-v1-dpo (REAL DPO format) DPO preference pairs for ARCHON alignment training. Schema (compatible with trl.DPOTrainer) { "prompt": "...", "chosen": [{"role": "system", "content": "..."}, {"role": "user", "content": "..."}, {"role": "assistant", "content": "

Open jescy525/archon-sft-v1-dpo on Hugging Face

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