Commit
•
9ab0ad3
1
Parent(s):
e12dd68
Update README.md
Browse files
README.md
CHANGED
|
@@ -3,3 +3,7 @@ This model is a T5-3B reranker fine-tuned on the MS MARCO passage dataset for 10
|
|
| 3 |
For more details on how to use it, check [pygaggle.ai](pygaggle.ai)
|
| 4 |
|
| 5 |
Paper describing the model: [Document Ranking with a Pretrained Sequence-to-Sequence Model](https://www.aclweb.org/anthology/2020.findings-emnlp.63/)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
For more details on how to use it, check [pygaggle.ai](pygaggle.ai)
|
| 4 |
|
| 5 |
Paper describing the model: [Document Ranking with a Pretrained Sequence-to-Sequence Model](https://www.aclweb.org/anthology/2020.findings-emnlp.63/)
|
| 6 |
+
|
| 7 |
+
This model is also the state of the art on the BEIR Benchmark.
|
| 8 |
+
Paper: [No Parameter Left Behind: How Distillation and Model Size Affect Zero-Shot Retrieval](https://arxiv.org/abs/2206.02873)
|
| 9 |
+
Repository: [Scaling Zero-shot Retrieval](https://github.com/guilhermemr04/scaling-zero-shot-retrieval)
|