The RLHFlow/Llama3-v2-iterative-DPO-iter2 galaxy

2 models are built on RLHFlow/Llama3-v2-iterative-DPO-iter2: 2 quantized, 0 fine-tuned, 0 adapters and 0 merges. Together they were downloaded 1,326 times in the last 30 days.

Most downloaded direct derivatives

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