update app.py

app.py

@@ -33,8 +33,8 @@ def evaluate_model(model_id):
         {
             "name": "MLQA Arabic",
             "dataset_id": "google/xtreme",
+            "subset": "MLQA.ar.ar",  # Specify the correct subset
             "split": "validation",
-            "subset": "MLQA.ar.ar",
             "size": 500,
             "columns": ("question", "context"),
             "sample_size": 100
@@ -52,11 +52,12 @@ def evaluate_model(model_id):
     evaluation_results = []
     
     for dataset_info in datasets_info:
-        # Load the dataset
-        dataset = load_dataset(dataset_info["dataset_id"], split=dataset_info["split"])
-        if dataset_info.get("subset"):
-            dataset = dataset.filter(lambda x: x["subset"] == dataset_info["subset"])
-
+        # Load the dataset with subset if available
+        if "subset" in dataset_info:
+            dataset = load_dataset(dataset_info["dataset_id"], dataset_info["subset"], split=dataset_info["split"])
+        else:
+            dataset = load_dataset(dataset_info["dataset_id"], split=dataset_info["split"])
+        
         # Sample the dataset
         dataset = dataset.select(range(min(dataset_info["sample_size"], len(dataset))))
         
@@ -122,4 +123,4 @@ demo = gr.Interface(
 
 # Launch the Gradio app
 if __name__ == "__main__":
-    demo.launch(debug= True)
+    demo.launch(debug = True)