Update README.md

README.md

@@ -14,6 +14,60 @@ language:
 - sk
 - sq
 pipeline_tag: token-classification
+model-index:
+  - name: xlmr-ner-slavic
+    results:
+      - task:
+          type: token-classification
+        metrics:
+          - name: Accuracy
+            type: Accuracy
+            value: 98.35
+          - name: F1-score
+            type: F1-score
+            value: 93.16
+          - name: Precision
+            type: Precision
+            value: 92.70
+          - name: Recall
+            type: Recall
+            value: 93.62
+          - name: LOC Precision
+            type: LOC Precision
+            value: 94.10
+          - name: LOC Recall
+            type: LOC Recall
+            value: 95.51
+          - name: LOC F1-score
+            type: LOC F1-score
+            value: 94.80
+          - name: MISC Precision
+            type: MISC Precision
+            value: 85.20
+          - name: MISC Recall
+            type: MISC Recall
+            value: 85.54
+          - name: MISC F1-score
+            type: MISC F1-score
+            value: 85.37
+          - name: ORG Precision
+            type: ORG Precision
+            value: 91.23
+          - name: ORG Recall
+            type: ORG Recall
+            value: 91.52
+          - name: ORG F1-score
+            type: ORG F1-score
+            value: 91.37
+          - name: PER Precision
+            type: PER Precision
+            value: 95.00
+          - name: PER Recall
+            type: PER Recall
+            value: 96.19
+          - name: PER F1-score
+            type: PER F1-score
+            value: 95.59
 ---
 ## XLM-Roberta-base NER model for slavic languages
 
@@ -28,7 +82,7 @@ We used the following hyper-parameters:
   * 40 epochs (preliminary runs showed  best F1-scores between epochs 15 and 35)
   * F1-score for best model selection and training progression.
 
-
+<!---
 ```
 {
   "xlmrb-sl_hr_sr_bs_mk_sq_cs_bg_pl_ru_sk_uk": {
@@ -63,7 +117,7 @@ We used the following hyper-parameters:
   }
 }
 ```
-
+-->
 Based on 
 [Analysis of Transfer Learning for Named Entity Recognition in South-Slavic Languages](https://aclanthology.org/2023.bsnlp-1.13) (Ivačič et al., BSNLP 2023)