Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# **PCL-Reasoner-V1.5: Advancing Math Reasoning with Offline Reinforcement Learning**
|
| 2 |
|
| 3 |
## Model Overview
|
|
@@ -126,4 +138,4 @@ All results are reported using the **Avg@32 metric** (average accuracy over 32 i
|
|
| 126 |
journal={arXiv preprint arXiv:2601.14716},
|
| 127 |
year={2026}
|
| 128 |
}
|
| 129 |
-
```
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
datasets:
|
| 4 |
+
- nvidia/Nemotron-Math-v2
|
| 5 |
+
metrics:
|
| 6 |
+
- accuracy
|
| 7 |
+
base_model:
|
| 8 |
+
- Qwen/Qwen2.5-32B
|
| 9 |
+
pipeline_tag: text-generation
|
| 10 |
+
tags:
|
| 11 |
+
- math
|
| 12 |
+
---
|
| 13 |
# **PCL-Reasoner-V1.5: Advancing Math Reasoning with Offline Reinforcement Learning**
|
| 14 |
|
| 15 |
## Model Overview
|
|
|
|
| 138 |
journal={arXiv preprint arXiv:2601.14716},
|
| 139 |
year={2026}
|
| 140 |
}
|
| 141 |
+
```
|