xinlai/DeepSeekMath-RL-Step-DPO download history
xinlai/DeepSeekMath-RL-Step-DPO is a 6.9B-parameter text generation model by xinlai. In the last 30 days it was downloaded 38 times (7 in the last 7 days), and 569 times in total.
It ranks #282,466 on the Hub by monthly downloads and #76,059 among text generation models.
It has 2 likes.
1 models build on DeepSeekMath-RL-Step-DPO: 1 quantized, 0 fine-tuned, 0 adapters and 0 merges. Together with the original they were downloaded 1,481 times in the last 30 days. See the DeepSeekMath-RL-Step-DPO galaxy.
Most downloaded derivatives
- mradermacher/DeepSeekMath-RL-Step-DPO-GGUF (quantized), 1.4K downloads in 30 days