Update tasks/text.py

tasks/text.py

@@ -62,22 +62,22 @@ 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)