Update README.md
Browse files
README.md
CHANGED
|
@@ -10,6 +10,8 @@ tags:
|
|
| 10 |
|
| 11 |
|
| 12 |
|
|
|
|
|
|
|
| 13 |
### Model Summary:
|
| 14 |
|
| 15 |
This model is a **Sentence Transformer** based on **Omartificial-Intelligence-Space/Arabic-Triplet-Matryoshka-V2**, fine-tuned for **semantic textual similarity** and **information retrieval** tasks. It maps sentences to dense vector representations for tasks like search, clustering, and text classification.
|
|
@@ -24,4 +26,19 @@ This model is a **Sentence Transformer** based on **Omartificial-Intelligence-Sp
|
|
| 24 |
- **Training Loss:** MatryoshkaLoss & MultipleNegativesRankingLoss.
|
| 25 |
- **Evaluation Metrics:** Cosine similarity-based metrics (Accuracy, Precision, Recall, NDCG).
|
| 26 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
This model is optimized for **legal document retrieval** and other NLP applications in Arabic.
|
|
|
|
| 10 |
|
| 11 |
|
| 12 |
|
| 13 |
+

|
| 14 |
+
|
| 15 |
### Model Summary:
|
| 16 |
|
| 17 |
This model is a **Sentence Transformer** based on **Omartificial-Intelligence-Space/Arabic-Triplet-Matryoshka-V2**, fine-tuned for **semantic textual similarity** and **information retrieval** tasks. It maps sentences to dense vector representations for tasks like search, clustering, and text classification.
|
|
|
|
| 26 |
- **Training Loss:** MatryoshkaLoss & MultipleNegativesRankingLoss.
|
| 27 |
- **Evaluation Metrics:** Cosine similarity-based metrics (Accuracy, Precision, Recall, NDCG).
|
| 28 |
|
| 29 |
+
---
|
| 30 |
+
|
| 31 |
+
## 🏆 Leaderboard Performance
|
| 32 |
+
|
| 33 |
+
The **Muffakir\_Embedding** model has achieved notable rankings on the [Arabic RAG Leaderboard](https://huggingface.co/spaces/Navid-AI/The-Arabic-Rag-Leaderboard), securing:
|
| 34 |
+
|
| 35 |
+
* * **🥇 1th place** in the **Islamic Dataset**
|
| 36 |
+
|
| 37 |
+
|
| 38 |
+
|
| 39 |
+
These results underscore the model's effectiveness in both retrieving relevant information and accurately ranking it within Arabic Retrieval-Augmented Generation (RAG) systems.
|
| 40 |
+
|
| 41 |
+
---
|
| 42 |
+
|
| 43 |
+
|
| 44 |
This model is optimized for **legal document retrieval** and other NLP applications in Arabic.
|