The ShenaoZ/0.0001_sft_nodpo_5iters_bs256_5102lr_iter_1 galaxy
4 models are built on ShenaoZ/0.0001_sft_nodpo_5iters_bs256_5102lr_iter_1: 0 quantized, 4 fine-tuned, 0 adapters and 0 merges. Together they were downloaded 63 times in the last 30 days.
Most downloaded direct derivatives
- ShenaoZ/0.0001_sft_nodpo_5iters_bs256_5102lr_iter_2 (finetune), 14 downloads in 30 days
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.