The kevinshin/qwen3-1.7b-rpo-lr-1e-5-alpha-1-beta-0.1-wc-cw-3k-neg-rethink-pos galaxy
2 models are built on kevinshin/qwen3-1.7b-rpo-lr-1e-5-alpha-1-beta-0.1-wc-cw-3k-neg-rethink-pos: 0 quantized, 2 fine-tuned, 0 adapters and 0 merges. Together they were downloaded 44 times in the last 30 days.
Most downloaded direct derivatives
- kevinshin/qwen3-1.7b-rpo-rpo-lr-1e-5-alpha-1-beta-0.1-wc-cw-3k-rethink-pos (finetune), 10 downloads in 30 days
- kevinshin/qwen3-1.7b-rpo-rpo-lr-1e-5-alpha-1-beta-0.1-wc-cw-3k-rethink-add-pos (finetune), 9 downloads in 30 days
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.