Update tasks/text.py

tasks/text.py

@@ -62,28 +62,28 @@ async def evaluate_text(request: TextEvaluationRequest):
 
     #--------------------------------------------------------------------------------------------
 
-    #load 
-    # Step 1: Use Sentence-BERT to convert text to embeddings
-    model = SentenceTransformer("dunzhang/stella_en_400M_v5",trust_remote_code=True,
-                                device="cpu",
-                                config_kwargs={"use_memory_efficient_attention": False, "unpad_inputs": False})
- 
-    # Convert each sentence into a vector representation (embedding)
-    embeddings = model.encode(test_dataset['quote'])
-    # YOUR MODEL INFERENCE CODE HERE
-    # Update the code below to replace the random baseline by your model inference within the inference pass where the energy consumption and emissions are tracked.
-    #--------------------------------------------------------------------------------------------   
-
-    #load model
-    with open("stella_400_xgb_500.pkl","rb") as f:
-        xgb = pickle.load(f)
-
+            """""#load 
+            # Step 1: Use Sentence-BERT to convert text to embeddings
+            model = SentenceTransformer("dunzhang/stella_en_400M_v5",trust_remote_code=True,
+                                        device="cpu",
+                                        config_kwargs={"use_memory_efficient_attention": False, "unpad_inputs": False})
+         
+            # Convert each sentence into a vector representation (embedding)
+            embeddings = model.encode(test_dataset['quote'])
+            # YOUR MODEL INFERENCE CODE HERE
+            # Update the code below to replace the random baseline by your model inference within the inference pass where the energy consumption and emissions are tracked.
+            #--------------------------------------------------------------------------------------------   
+        
+            #load model
+            with open("stella_400_xgb_500.pkl","rb") as f:
+                xgb = pickle.load(f)
+        """""
     #predictions = xgb.predict(embeddings)
         
     
     # Make random predictions (placeholder for actual model inference)
     true_labels = test_dataset["label"]
-    predictions = xgb.predict(embeddings)
+    #predictions = xgb.predict(embeddings)
 
     #--------------------------------------------------------------------------------------------
     # YOUR MODEL INFERENCE STOPS HERE
@@ -94,7 +94,7 @@ async def evaluate_text(request: TextEvaluationRequest):
     emissions_data = tracker.stop_task()
     
     # Calculate accuracy
-    accuracy = accuracy_score(true_labels, predictions)
+    accuracy = accuracy_score(true_labels, np.array([1]*len(true_labels))
     
     # Prepare results dictionary
     results = {