Update README.md
Browse files
README.md
CHANGED
|
@@ -1,9 +1,3 @@
|
|
| 1 |
-
GPG: A Simple and Strong Reinforcement Learning
|
| 2 |
-
Baseline for Model Reasoning
|
| 3 |
-
https://arxiv.org/abs/2504.02546
|
| 4 |
-
|
| 5 |
-
The RL model trained on the Open-r1 dataset based on GPG, using DeepSeek-R1-Distill-Qwen-1.5B as the baseline model.
|
| 6 |
-
|
| 7 |
---
|
| 8 |
license: apache-2.0
|
| 9 |
datasets:
|
|
@@ -14,4 +8,9 @@ metrics:
|
|
| 14 |
- accuracy
|
| 15 |
base_model:
|
| 16 |
- deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
|
| 17 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
datasets:
|
|
|
|
| 8 |
- accuracy
|
| 9 |
base_model:
|
| 10 |
- deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
|
| 11 |
+
---
|
| 12 |
+
GPG: A Simple and Strong Reinforcement Learning
|
| 13 |
+
Baseline for Model Reasoning
|
| 14 |
+
https://arxiv.org/abs/2504.02546
|
| 15 |
+
|
| 16 |
+
The RL model trained on the Open-r1 dataset based on GPG, using DeepSeek-R1-Distill-Qwen-1.5B as the baseline model.
|