Dongfu Jiang
commited on
Commit
•
28afd59
1
Parent(s):
bfd2da5
Update README.md
Browse files
README.md
CHANGED
|
@@ -81,6 +81,7 @@ print(comparison_results)
|
|
| 81 |
# tensor([ True, False], device='cuda:0'), which means whether candidate A is better than candidate B for each input
|
| 82 |
```
|
| 83 |
|
|
|
|
| 84 |
|
| 85 |
|
| 86 |
# Pairwise Reward Model for LLMs (PairRM) from LLM-Blender
|
|
|
|
| 81 |
# tensor([ True, False], device='cuda:0'), which means whether candidate A is better than candidate B for each input
|
| 82 |
```
|
| 83 |
|
| 84 |
+
**We still recommend using the llm-blender wrapper to use the PairRM, as many useful application functions have been implemented to support various scenarios, such as rank, and conversation comparisons, best-of-n-sampling, etc.**
|
| 85 |
|
| 86 |
|
| 87 |
# Pairwise Reward Model for LLMs (PairRM) from LLM-Blender
|