Update README.md

README.md

@@ -142,6 +142,30 @@ You can finetune this model on your own dataset.
 
 ### Evaluation Dataset
 
+---
+model-index:
+  - name: Yi-34B
+    results:
+      - task:
+          type: text-ranking
+        dataset:
+          name: Custom UIT-R2GQA using [mine_hard_negatives()](https://sbert.net/docs/package_reference/util.html#sentence_transformers.util.mine_hard_negatives)
+        metrics:
+          - name: valid_map
+            value: 0.9969199178644764
+          - name: valid_mrr@10
+            value: 0.9969199178644764
+          - name: valid_ndcg@10
+            value: 0.9977264666544443
+            
+          - name: test_map
+            value: 0.9969262295081968
+          - name: test_mrr@10
+            value: 0.9969262295081968
+          - name: test_ndcg@10
+            value: 0.9977311255342508
+---
+
 #### Unnamed Dataset
 
 * Size: 974 evaluation samples