The yifengw3/tulu3-olmo3-1125-32b-DPO-training-5epochs_1e-5 galaxy

5 models are built on yifengw3/tulu3-olmo3-1125-32b-DPO-training-5epochs_1e-5: 0 quantized, 5 fine-tuned, 0 adapters and 0 merges. Together they were downloaded 142 times in the last 30 days.

Most downloaded direct derivatives

• yifengw3/tulu3-olmo3-1125-32b-unsafe-from-DPO-training-3000samples (finetune), 30 downloads in 30 days
• yifengw3/tulu3-olmo3-1125-32b-unsafe-from-DPO-training-2000samples (finetune), 29 downloads in 30 days
• yifengw3/tulu3-olmo3-1125-32b-unsafe-from-DPO-training-4500samples (finetune), 20 downloads in 30 days
• yifengw3/tulu3-olmo3-1125-32b-unsafe-from-DPO-training-500samples (finetune), 19 downloads in 30 days
• yifengw3/tulu3-olmo3-1125-32b-unsafe-from-DPO-training-1000samples (finetune), 15 downloads in 30 days

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