Update app.py

app.py

@@ -21,15 +21,13 @@ 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")
 
-    # Generate tokens
     gen_tokens = model.generate(
-        input_ids['input_ids'], 
-        max_length=max_new_tokens + input_ids['input_ids'].shape[1],  # Adjusting max_length to account for input length
+        input_ids = input_ids, 
+        max_new_tokens=max_new_tokens
         do_sample=True, 
         temperature=temperature,
     )
 
-    # Decode tokens to string
     gen_text = tokenizer.decode(gen_tokens[0])
     return gen_text