The tsavage68/Error_Q1.5_500steps_1e6rate_SFT galaxy
1 models are built on tsavage68/Error_Q1.5_500steps_1e6rate_SFT: 0 quantized, 1 fine-tuned, 0 adapters and 0 merges. Together they were downloaded 15 times in the last 30 days.
Most downloaded direct derivatives
- tsavage68/deepseek-r1-distilled-Qwen-1.5B-GRPO (finetune), 10 downloads in 30 days
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.