Update README.md
Browse files
README.md
CHANGED
|
@@ -101,4 +101,14 @@ with torch.no_grad():
|
|
| 101 |
|
| 102 |
scores = [score[0] for score in logits]
|
| 103 |
print(scores)
|
| 104 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 101 |
|
| 102 |
scores = [score[0] for score in logits]
|
| 103 |
print(scores)
|
| 104 |
+
```
|
| 105 |
+
|
| 106 |
+
## Performance
|
| 107 |
+
In the following table, we provide various pre-trained Cross-Encoders together with their performance on the [MS MMarco Passage Reranking - Vi - Dev](https://huggingface.co/datasets/unicamp-dl/mmarco) dataset.
|
| 108 |
+
|
| 109 |
+
| Model-Name | NDCG@3 | MRR@3 | NDCG@5 | MRR@5 | NDCG@10 | MRR@10 | Docs / Sec |
|
| 110 |
+
| ------------------------------- |:------ | :---- |:------ | :---- |:------ | :----| :--- |
|
| 111 |
+
|itdainb/vietnamese-cross-encoder |0.6624|0.6433|0.7147|0.6706|0.7422|0.6804|3.19
|
| 112 |
+
|BAAI/bge-reranker-v2-m3 |0.6094|0.5841|0.6515|0.6062|0.6874|0.6209|0.58
|
| 113 |
+
|
| 114 |
+
Note: Runtime was computed on a A100 GPU.
|