Update app.py

app.py

@@ -20,7 +20,7 @@ model = AutoModelForCausalLM.from_pretrained(model_id, quantization_config=bnb_c
 def generate_response(user_input, max_new_tokens, temperature):
     messages = [{"role": "user", "content": user_input}]
     input_ids = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt")
-
+    input_ids = input_ids.to(model.device)
     gen_tokens = model.generate(
         input_ids = input_ids, 
         max_new_tokens=max_new_tokens,