Update tasks/text.py

tasks/text.py

@@ -38,27 +38,13 @@ async def evaluate_text(request: TextEvaluationRequest):
     }
 
     # Load and prepare the dataset
-    dataset = load_dataset(request.dataset_name)
+    dataset = load_dataset(request.dataset_name, token=os.getenv("HF_TOKEN"))
 
     # Convert string labels to integers
     dataset = dataset.map(lambda x: {"label": LABEL_MAPPING[x["label"]]})
 
     # Split dataset
-    train_test = dataset["train"]
     test_dataset = dataset["test"]
-    
-    # Start tracking emissions
-    tracker.start()
-    tracker.start_task("inference")
-
-    #--------------------------------------------------------------------------------------------
-    # 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.
-    #--------------------------------------------------------------------------------------------   
-    
-    # Make random predictions (placeholder for actual model inference)
-    #true_labels = test_dataset["label"]
-    #predictions = [random.randint(0, 7) for _ in range(len(true_labels))]
 
     from transformers import AutoModelForSequenceClassification, AutoTokenizer
     import torch
@@ -77,6 +63,21 @@ async def evaluate_text(request: TextEvaluationRequest):
     model.to(device)
     model.eval()  # Set to evaluation mode
 
+    
+    # Start tracking emissions
+    tracker.start()
+    tracker.start_task("inference")
+
+    #--------------------------------------------------------------------------------------------
+    # 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.
+    #--------------------------------------------------------------------------------------------   
+    
+    # Make random predictions (placeholder for actual model inference)
+    #true_labels = test_dataset["label"]
+    #predictions = [random.randint(0, 7) for _ in range(len(true_labels))]
+
+
 
     # tokenize texts
     test_encodings = tokenizer(test_dataset["quote"], padding='max_length', truncation=True, max_length=MAX_LENGTH, return_tensors="pt")