The AmberYifan/Qwen2.5-14B-Instruct-ultrafeedback-DRIFT-iter2-RPO galaxy

1 models are built on AmberYifan/Qwen2.5-14B-Instruct-ultrafeedback-DRIFT-iter2-RPO: 1 quantized, 0 fine-tuned, 0 adapters and 0 merges. Together they were downloaded 229 times in the last 30 days.

Most downloaded direct derivatives

• mradermacher/Qwen2.5-14B-Instruct-ultrafeedback-DRIFT-iter2-RPO-GGUF (quantized), 208 downloads in 30 days

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