Update README.md

README.md

@@ -59,13 +59,15 @@ array([[0.66212064, 0.33066642],
 
 | Model                | Accuracy@1 | Accuracy@3 | Accuracy@5 | Accuracy@10  |  MRR@10 |
 |----------------------|------------|------------|------------|-------------|--------------|
-| Vietnamese Reranker (Phase 2)            | 0.7944     | 0.9324    | 0.9537     | 0.9740     | 0.8672       | 
+| Vietnamese_Reranker (Phase 2)            | 0.7944     | 0.9324    | 0.9537     | 0.9740     | 0.8672       | 
 | Vietnamese_Embedding (Phase 2)          | 0.7262     | 0.8927     | 0.9268     | 0.9578     | 0.8149       | 
 | Vietnamese_Embedding  (public)          | 0.7274     | 0.8992     | 0.9305     | 0.9568     | 0.8181       | 
 | Vietnamese-bi-encoder (BKAI)         | 0.7109     | 0.8680     | 0.9014     | 0.9299      | 0.7951       | 
 | BGE-M3 | 0.5682     | 0.7728     | 0.8382     | 0.8921      | 0.6822       |
 
-Vietnamese Reranker (Phase 2) and Vietnamese Reranker (Phase 2) was trained on 1100000 triplets. Although the score on the legal domain drops a bit on Vietnamese_Embedding (Phase 2), since this phase data is much larger, it is very good for other domains.
+Vietnamese_Reranker (Phase 2) and Vietnamese_Embedding (Phase 2) was trained on 1100000 triplets. 
+
+Although the score on the legal domain drops a bit on Vietnamese_Embedding (Phase 2), since this phase data is much larger, it is very good for other domains.
 
 You can reproduce the evaluation result by running code python evaluation_model.py (data downloaded from Kaggle).