The wh-zhu/qwen2_1.5B-ultrachatfeedback-dpo galaxy

1 models are built on wh-zhu/qwen2_1.5B-ultrachatfeedback-dpo: 0 quantized, 1 fine-tuned, 0 adapters and 0 merges. Together they were downloaded 34 times in the last 30 days.

Most downloaded direct derivatives

• pltops/qwen2_7B-dis-wspo-full_E1 (finetune), 19 downloads in 30 days

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