Update tasks/text.py

tasks/text.py

@@ -45,24 +45,14 @@ 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))]
@@ -78,6 +68,17 @@ async def evaluate_text(request: TextEvaluationRequest):
     model = AutoModelForSequenceClassification.from_pretrained(path_model).half().to(device)  # Model en half precision sur GPU
     tokenizer = AutoTokenizer.from_pretrained(path_tokenizer)
     
+    
+    # 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.
+    #--------------------------------------------------------------------------------------------   
+    
+
     # Fonction de préprocessing
     def preprocess_function(df):
         tokenized = tokenizer(df["quote"], truncation=True) # Removed padding here