Update README.md
Browse files
README.md
CHANGED
|
@@ -12,7 +12,7 @@ library_name: transformers
|
|
| 12 |
---
|
| 13 |
|
| 14 |
# CodeRM-NT
|
| 15 |
-
[Paper](
|
| 16 |
[Github](https://github.com/THUDM/CodeRM-NT)
|
| 17 |
|
| 18 |
Providing accurate reward signals for code generated by LLMs is a significant challenge in applying reinforcement learning (RL) to code generation. Existing methods rely on unit tests, which are expensive to curate and unreliable when automatically synthesized.
|
|
|
|
| 12 |
---
|
| 13 |
|
| 14 |
# CodeRM-NT
|
| 15 |
+
[Paper](https://github.com/THUDM/CodeRM-NT/blob/main/assets/CodeRM-NT.pdf) |
|
| 16 |
[Github](https://github.com/THUDM/CodeRM-NT)
|
| 17 |
|
| 18 |
Providing accurate reward signals for code generated by LLMs is a significant challenge in applying reinforcement learning (RL) to code generation. Existing methods rely on unit tests, which are expensive to curate and unreliable when automatically synthesized.
|