Add library name, pipeline tag and link to code
#1
by
nielsr
HF Staff
- opened
README.md
CHANGED
|
@@ -1,16 +1,20 @@
|
|
| 1 |
---
|
| 2 |
-
|
|
|
|
| 3 |
datasets:
|
| 4 |
- knoveleng/open-rs
|
| 5 |
language:
|
| 6 |
- en
|
|
|
|
| 7 |
metrics:
|
| 8 |
- accuracy
|
| 9 |
-
|
| 10 |
-
|
| 11 |
---
|
| 12 |
-
|
| 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.
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
base_model:
|
| 3 |
+
- deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
|
| 4 |
datasets:
|
| 5 |
- knoveleng/open-rs
|
| 6 |
language:
|
| 7 |
- en
|
| 8 |
+
license: apache-2.0
|
| 9 |
metrics:
|
| 10 |
- accuracy
|
| 11 |
+
library_name: transformers
|
| 12 |
+
pipeline_tag: text-generation
|
| 13 |
---
|
| 14 |
+
|
| 15 |
+
GPG: A Simple and Strong Reinforcement Learning Baseline for Model Reasoning
|
| 16 |
https://arxiv.org/abs/2504.02546
|
| 17 |
|
| 18 |
+
The RL model trained on the Open-r1 dataset based on GPG, using DeepSeek-R1-Distill-Qwen-1.5B as the baseline model.
|
| 19 |
+
|
| 20 |
+
Code: https://github.com/AMAP-ML/GPG
|