Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,20 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model:
|
| 4 |
+
- Qwen/Qwen2.5-Math-7B
|
| 5 |
+
---
|
| 6 |
+
|
| 7 |
+
## Model ID
|
| 8 |
+
|
| 9 |
+
GPG: A Simple and Strong Reinforcement Learning Baseline for Model Reasoning
|
| 10 |
+
|
| 11 |
+
https://arxiv.org/abs/2504.02546
|
| 12 |
+
|
| 13 |
+
## Model Details
|
| 14 |
+
|
| 15 |
+
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.
|
| 16 |
+
|
| 17 |
+
## Attention!
|
| 18 |
+
|
| 19 |
+
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.
|
| 20 |
+
|