fix error

app.py

@@ -22,7 +22,7 @@ async def generate_response(chat_input: ChatInput):
         inputs = tokenizer.encode(prompt, return_tensors="pt", add_special_tokens=False)
 	
         # Generate a response
-        outputs = model.generate(inputs, max_length=1000, num_return_sequences=1, pad_token_id=tokenizer.eos_token)
+        outputs = model.generate(inputs, max_length=1000, num_return_sequences=1)
         response = tokenizer.decode(outputs[0], skip_special_tokens=True)
 
         # Extract only the assistant's response