Update README.md

README.md

@@ -25,24 +25,14 @@ model-index:
       name: amh passage retrieval dev
       type: amh-passage-retrieval-dev
     metrics:
-    - type: map
-      value: 0.8534696098981692
-      name: Map
     - type: mrr@10
-      value: 0.8529139384920634
+      value: 0.83
       name: Mrr@10
     - type: ndcg@10
-      value: 0.8815092346456579
-      name: Ndcg@10
-    - type: map
-      value: 0.8531100005859653
-      name: Map
-    - type: mrr@10
-      value: 0.8513254037953979
-      name: Mrr@10
-    - type: ndcg@10
-      value: 0.8802377937215004
+      value: 0.856
       name: Ndcg@10
+datasets:
+- rasyosef/Amharic-Passage-Retrieval-Dataset-V2
 ---
 
 # roberta-amharic-reranker-base
@@ -82,7 +72,7 @@ Then you can load this model and run inference.
 from sentence_transformers import CrossEncoder
 
 # Download from the 🤗 Hub
-model = CrossEncoder("rasyosef/RoBERTa-Amharic-Reranker-Base")
+model = CrossEncoder("rasyosef/reranker-amharic-base")
 # Get scores for pairs of texts
 
 pairs = [
@@ -150,25 +140,8 @@ You can finetune this model on your own dataset.
 
 | Metric      | Value      |
 |:------------|:-----------|
-| map         | 0.8535     |
-| mrr@10      | 0.8529     |
-| **ndcg@10** | **0.8815** |
-
-#### Cross Encoder Reranking
-
-* Dataset: `amh-passage-retrieval-dev`
-* Evaluated with [<code>CrossEncoderRerankingEvaluator</code>](https://sbert.net/docs/package_reference/cross_encoder/evaluation.html#sentence_transformers.cross_encoder.evaluation.CrossEncoderRerankingEvaluator) with these parameters:
-  ```json
-  {
-      "at_k": 10
-  }
-  ```
-
-| Metric      | Value      |
-|:------------|:-----------|
-| map         | 0.8531     |
-| mrr@10      | 0.8513     |
-| **ndcg@10** | **0.8802** |
+| mrr@10      | 0.830     |
+| **ndcg@10** | **0.856** |
 
 <!--
 ## Bias, Risks and Limitations
@@ -184,6 +157,8 @@ You can finetune this model on your own dataset.
 
 ## Training Details
 
+<details>
+
 ### Training Dataset
 
 #### Unnamed Dataset
@@ -363,22 +338,9 @@ You can finetune this model on your own dataset.
 - Datasets: 3.6.0
 - Tokenizers: 0.21.1
 
-## Citation
+</details>
 
-### BibTeX
-
-#### Sentence Transformers
-```bibtex
-@inproceedings{reimers-2019-sentence-bert,
-    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
-    author = "Reimers, Nils and Gurevych, Iryna",
-    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
-    month = "11",
-    year = "2019",
-    publisher = "Association for Computational Linguistics",
-    url = "https://arxiv.org/abs/1908.10084",
-}
-```
+## Citation
 
 <!--
 ## Glossary