Update README.md
Browse files
README.md
CHANGED
|
@@ -125,6 +125,8 @@ print(beta_reward)
|
|
| 125 |
```
|
| 126 |
|
| 127 |
## Evaluation
|
|
|
|
|
|
|
| 128 |
|
| 129 |
### Evaluation Base Model
|
| 130 |
|
|
|
|
| 125 |
```
|
| 126 |
|
| 127 |
## Evaluation
|
| 128 |
+
### Evaluation Code
|
| 129 |
+
We use codes in [Implicit PRM](https://github.com/PRIME-RL/ImplicitPRM/tree/main/eval) to evaluate the performance of EurusPRM. The reference model is **Qwen2.5-Math-7B-Instruct**.
|
| 130 |
|
| 131 |
### Evaluation Base Model
|
| 132 |
|