xinlai/DeepSeekMath-RL-Step-DPO
Text Generation
•
Updated
•
11
•
1
Step-DPO
Resources for "Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs"
-
-
xinlai/Qwen2-7B-Instruct-Step-DPO
Text Generation • Updated • 675 • 2 -
xinlai/Qwen2-72B-Instruct-Step-DPO
Text Generation • Updated • 26 -
xinlai/DeepSeekMath-Base-SFT-Step-DPO
Text Generation • Updated • 16 -
xinlai/Qwen2-7B-SFT-Step-DPO
Text Generation • Updated • 13 -
xinlai/Qwen1.5-32B-SFT-Step-DPO
Text Generation • Updated • 13 • 1 -
xinlai/Qwen2-57B-A14B-SFT-Step-DPO
Text Generation • Updated • 17 • 1 -
xinlai/Llama-3-70B-SFT-Step-DPO
Text Generation • Updated • 18 -
xinlai/Qwen2-72B-SFT-Step-DPO
Text Generation • Updated • 8 • 1 -
xinlai/Math-Step-DPO-10K
Viewer • Updated • 10.8k • 543 • 29 -
Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs
Paper • 2406.18629 • Published • 41