Downloads · 30 days
23
10% of all-time downloads
Qwen2-57B-A14B-SFT-Step-DPO
xinlai/Qwen2-57B-A14B-SFT-Step-DPO
Qwen2-57B-A14B-SFT-Step-DPO is a text generation model from xinlai. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
All-time downloads
241
Public
Parameters
57.4B
115 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors115 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Model type
- qwen2_moe
- Access
- Public
- Created
- Jun 25, 2024
- Updated
- Jun 28, 2024
- SHA
- 1fc3ae84
Try a prompt
Model card
From the Hugging Face model README
Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs
This repo contains the Qwen2-57B-A14B-SFT-Step-DPO model. It is obtained by performing Step-DPO on Qwen2-57B-A14B-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
- Task
- Text Generation
- Library
- transformers
- Type
- qwen2_moe
- License
- apache-2.0
- Created
- Jun 25, 2024
- Updated
- Jun 28, 2024