Update app.py

app.py

@@ -24,13 +24,13 @@ def load_and_preprocess_data():
                 example, 
                 truncation=True, 
                 padding='max_length', 
-                max_length=4
+                max_length=32
             )
             rejected_tokenized = tokenizer(
                 example, 
                 truncation=True, 
                 padding='max_length', 
-                max_length=4
+                max_length=32
             )
             
             combined_input_ids = chosen_tokenized['input_ids'] + rejected_tokenized['input_ids']
@@ -40,7 +40,7 @@ def load_and_preprocess_data():
             # Ensure labels match the exact length of input_ids
             inputs['input_ids'].append(combined_input_ids)
             inputs['attention_mask'].append(combined_attention_mask)
-            inputs['labels'].append(torch.tensor([1] * (label_length // 2) + [0] * (label_length - label_length // 2)))
+            inputs['labels'].append(torch.tensor([1] * (label_length // 16) + [0] * (label_length - label_length // 16)))
     
         # Convert lists to tensors for each batch
         inputs['input_ids'] = torch.tensor(inputs['input_ids'], dtype=torch.long)
@@ -101,7 +101,7 @@ def train_model(dataset):
 # Gradio Interface function to predict
 def predict(text):
     # Tokenize the input text
-    inputs = tokenizer(text, return_tensors="pt", padding=True, truncation=True, max_length=4)  # Adjust max_length to match preprocessing
+    inputs = tokenizer(text, return_tensors="pt", padding=True, truncation=True, max_length=32)  # Adjust max_length to match preprocessing
     # Perform inference
     outputs = model(**inputs)
     prediction = torch.argmax(outputs.logits, dim=-1).item()  # Get the class with the highest score