Downloads · 30 days
12
6% of all-time downloads
Qwen2.5-Math-7B-GPG
GD-ML/Qwen2.5-Math-7B-GPG
Qwen2.5-Math-7B-GPG is a machine learning model from GD-ML. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
GPG: A Simple and Strong Reinforcement Learning Baseline for Model Reasoning
All-time downloads
198
Public
Parameters
7.6B
15.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors15.2 GB · 100%
At a glance
- License
- apache-2.0
- Model type
- qwen2
- Access
- Public
- Created
- Apr 30, 2025
- Updated
- Apr 30, 2025
- SHA
- 95d11f4c
Base models
Model card
From the Hugging Face model README
Model ID
GPG: A Simple and Strong Reinforcement Learning Baseline for Model Reasoning
https://arxiv.org/abs/2504.02546
Model Details
The RL model (GPG-7B in paper) trained on the simple1r_qwen_level3to5 dataset based on GPG, using Qwen2.5-Math-7B as the baseline model.
Attention!
Due to changes in environment and devices, test results may fluctuate. Specifically, when tested on an NPU, the average accuracy of five datasets (AIME24, AMC23, MATH-500, Minerva and OlympiadBench) is 57.7. However, when tested on an H20 GPU, the average accuracy drops from 57.7 to 55.3. These fluctuations are entirely within an acceptable range.
- Type
- qwen2
- License
- apache-2.0
- Created
- Apr 30, 2025
- Updated
- Apr 30, 2025