Update app.py

app.py

@@ -29,8 +29,12 @@ def respond(message, history: list[tuple[str, str]], system_message, max_tokens,
         return_tensors="pt",  # Return tensors for PyTorch
     )
 
+    # Debug inputs
+    print("Inputs:", inputs)
+
     # Extract input_ids correctly
-    input_ids = inputs["input_ids"]
+    input_ids = inputs["input_ids"]  # Ensure the correct field is used
+    print("Input IDs shape:", input_ids.shape)
 
     # Generate response
     output = model.generate(
@@ -41,6 +45,10 @@ def respond(message, history: list[tuple[str, str]], system_message, max_tokens,
         min_p=min_p,
     )
 
+    # Debug output
+    print("Generated Output Shape:", output.shape)
+    print("Generated Output:", output)
+
     # Decode and format the response
     # Use `decode` for the first sequence in the batch
     response = tokenizer.decode(output[0], skip_special_tokens=True)