The lblaoke/opt-350m-hh-rlhf-chosen-sft-trl-v5 galaxy

1 models are built on lblaoke/opt-350m-hh-rlhf-chosen-sft-trl-v5: 0 quantized, 1 fine-tuned, 0 adapters and 0 merges. Together they were downloaded 21 times in the last 30 days.

Most downloaded direct derivatives

• lblaoke/opt-350m-hh-rlhf-dpo-trl-v5 (finetune), 8 downloads in 30 days

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