Resources for "Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs"
Xin Lai
xinlai
AI & ML interests
Multimodal LLM, LLM Reasoning, Point Cloud Segmentation, Image Segmentation
Recent Activity
upvoted a paper about 1 month ago
Beyond Data Scaling: Representation-Centric Continued Pre-training for Vision-Language-Action Models liked a model 3 months ago
tencent/Hy3 upvoted a paper 3 months ago
Training Open Models for Agentic Phone UseOrganizations
None yet
models 21
xinlai/Qwen2-7B-Instruct-Step-DPO
Text Generation • 8B • Updated • 27 • 3
xinlai/Qwen2-57B-A14B-SFT-Step-DPO
Text Generation • 57B • Updated • 21 • 1
xinlai/Qwen1.5-32B-SFT-Step-DPO
Text Generation • 33B • Updated • 19 • 1
xinlai/Llama-3-70B-SFT-Step-DPO
Text Generation • 71B • Updated • 22
xinlai/DeepSeekMath-Base-SFT-Step-DPO
Text Generation • 7B • Updated • 33
xinlai/Qwen2-7B-SFT-Step-DPO
Text Generation • 8B • Updated • 17
xinlai/Qwen2-72B-Instruct-Step-DPO
Text Generation • 73B • Updated • 11
xinlai/DeepSeekMath-RL-Step-DPO
Text Generation • 7B • Updated • 38 • 2
xinlai/Qwen2-57B-A14B-SFT
Text Generation • 57B • Updated • 15
xinlai/Qwen1.5-32B-SFT
Text Generation • 33B • Updated • 15