The xinlai/DeepSeekMath-Base-SFT-Step-DPO galaxy

1 models are built on xinlai/DeepSeekMath-Base-SFT-Step-DPO: 1 quantized, 0 fine-tuned, 0 adapters and 0 merges. Together they were downloaded 280 times in the last 30 days.

Most downloaded direct derivatives