Add evaluation results for IRIISNEPAL/RoBERTa_Nepali_110M on Nep-gLUE tasks

README.md

@@ -12,6 +12,60 @@ language:
 metrics:
 - f1
 - accuracy
+model-index:
+- name: IRIISNEPAL/RoBERTa_Nepali_110M
+  results:
+  - task:
+      type: token-classification
+      name: Named Entity Recognition (NER)
+    dataset:
+      type: nep_glue
+      name: Nep-gLUE
+    metrics:
+      - type: f1
+        name: Macro F1 Score
+        value: 93.74
+
+  - task:
+      type: token-classification
+      name: Part-of-Speech (POS) Tagging
+    dataset:
+      type: nep_glue
+      name: Nep-gLUE
+    metrics:
+      - type: f1
+        name: Macro F1 Score
+        value: 97.52
+
+  - task:
+      type: text-classification
+      name: Categorical Classification (CC)
+    dataset:
+      type: nep_glue
+      name: Nep-gLUE
+    metrics:
+      - type: f1
+        name: Macro F1 Score
+        value: 94.68
+
+  - task:
+      type: similarity
+      name: Categorical Pair Similarity (CPS)
+    dataset:
+      type: nep_glue
+      name: Nep-gLUE
+    metrics:
+      - type: f1
+        name: Macro F1 Score
+        value: 96.49
+
+  - task:
+      type: overall-benchmark
+      name: Nep-gLUE
+    metrics:
+      - type: score
+        name: Overall Score
+        value: 95.60
 ---
 
 # Model Card for Model ID
@@ -144,8 +198,7 @@ The model was evaluated on the [Nepali Language Evaluation Benchmark (Nep-gLUE)]
 
 <!-- These are the evaluation metrics being used, ideally with a description of why. -->
 
-- Accuracy
-- F1 Score
+- **Macro-F1** for the [Nepali Language Understanding Evaluation (Nep-gLUE)](https://nepberta.github.io/nepglue/) benchmark.
 
 ### Results