Update README.md
Browse files
README.md
CHANGED
|
@@ -3,6 +3,15 @@ license: mit
|
|
| 3 |
pipeline_tag: sentence-similarity
|
| 4 |
---
|
| 5 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
This model is the corresponding re-ranker supervised by instruction-tuned Llama2-13B, check our paper for more details.
|
| 7 |
|
| 8 |
The model generates a relevance score directly during ranking. Please replace the re-ranker argument in the scripts with model id.
|
|
|
|
| 3 |
pipeline_tag: sentence-similarity
|
| 4 |
---
|
| 5 |
|
| 6 |
+
Update (Dec 31, 2024):
|
| 7 |
+
|
| 8 |
+
We have updated our model.
|
| 9 |
+
1. The previous version uses [ms-marco-MiniLM-L-6-v2](https://huggingface.co/cross-encoder/ms-marco-MiniLM-L-6-v2) as base model,
|
| 10 |
+
the updated version takes [ms-marco-MiniLM-L-12-v2](https://huggingface.co/cross-encoder/ms-marco-MiniLM-L-12-v2) as base model which shows better generality
|
| 11 |
+
and performance improvements.
|
| 12 |
+
|
| 13 |
+
2. The new model uses confidence threshold of 0.8 compared to prior model without confidence-based training.
|
| 14 |
+
|
| 15 |
This model is the corresponding re-ranker supervised by instruction-tuned Llama2-13B, check our paper for more details.
|
| 16 |
|
| 17 |
The model generates a relevance score directly during ranking. Please replace the re-ranker argument in the scripts with model id.
|