xinlai/DeepSeekMath-RL-Step-DPO
Text Generation
•
Updated
•
12
•
2
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 • 11 • 2 -
xinlai/Qwen2-72B-Instruct-Step-DPO
Text Generation • Updated • 15 -
xinlai/DeepSeekMath-Base-SFT-Step-DPO
Text Generation • Updated • 3 -
xinlai/Qwen2-7B-SFT-Step-DPO
Text Generation • Updated • 4 -
xinlai/Qwen1.5-32B-SFT-Step-DPO
Text Generation • Updated • 4 • 1 -
xinlai/Qwen2-57B-A14B-SFT-Step-DPO
Text Generation • Updated • 5 • 1 -
xinlai/Llama-3-70B-SFT-Step-DPO
Text Generation • Updated • 9 -
xinlai/Qwen2-72B-SFT-Step-DPO
Text Generation • Updated • 5 • 1 -
xinlai/Math-Step-DPO-10K
Viewer • Updated • 10.8k • 633 • 52 -
Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs
Paper • 2406.18629 • Published • 43