Step-DPO
Collection
Resources for "Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs"
•
11 items
•
Updated
•
3
Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs
This repo contains the Qwen2-7B-SFT-Step-DPO model. It is obtained by performing Step-DPO on Qwen2-7B-SFT.
Step-DPO is a simple, effective, and data-efficient method for boosting the mathematical reasoning ability of LLMs. Notably, Step-DPO, when applied to Qwen2-72B-Instruct, achieves scores of 70.8% and 94.0% on the test sets of MATH and GSM8K without bells and wistles, respectively, surpassing a series of closed-source models, including GPT-4-1106, Claude-3-Opus, and Gemini-1.5-Pro.
Contact
- Downloads last month
- 261
This model does not have enough activity to be deployed to Inference API (serverless) yet.
Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.