Update README.md
Browse files
README.md
CHANGED
@@ -1,4 +1,4 @@
|
|
1 |
-
Process reward
|
2 |
|
3 |
`Input`: question + step-by-step solutions with a special step tag `ки`, e.g.,
|
4 |
```
|
|
|
1 |
+
Process reward model (mistral-7b) used in [Math-Shepherd](https://arxiv.org/pdf/2312.08935.pdf).
|
2 |
|
3 |
`Input`: question + step-by-step solutions with a special step tag `ки`, e.g.,
|
4 |
```
|