The AmberYifan/Qwen2.5-7B-Instruct-wildfeedback-iterDPO-iter2 galaxy
1 models are built on AmberYifan/Qwen2.5-7B-Instruct-wildfeedback-iterDPO-iter2: 1 quantized, 0 fine-tuned, 0 adapters and 0 merges. Together they were downloaded 185 times in the last 30 days.
Most downloaded direct derivatives
- mradermacher/Qwen2.5-7B-Instruct-userfeedback-on-policy-iter2-GGUF (quantized), 161 downloads in 30 days
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.