Update README.md
Browse files
README.md
CHANGED
|
@@ -136,6 +136,8 @@ This model has three main benefits over comparable rerankers.
|
|
| 136 |
This last point means that this model can be used natively with many widely available inference packages, including vLLM and LMDeploy.
|
| 137 |
This in turns allows our reranker to benefit from improvements to inference as and when these packages release them.
|
| 138 |
|
|
|
|
|
|
|
| 139 |
# How to use
|
| 140 |
|
| 141 |
The model was trained to expect an input such as:
|
|
|
|
| 136 |
This last point means that this model can be used natively with many widely available inference packages, including vLLM and LMDeploy.
|
| 137 |
This in turns allows our reranker to benefit from improvements to inference as and when these packages release them.
|
| 138 |
|
| 139 |
+
Update: We have also found that this model works pretty well as a code snippet reranker too (P@1 of 96%)! See our [Colab](https://colab.research.google.com/drive/1ABL1xaarekLIlVJKbniYhXgYu6ZNwfBm?usp=sharing) for more details.
|
| 140 |
+
|
| 141 |
# How to use
|
| 142 |
|
| 143 |
The model was trained to expect an input such as:
|