Update app.py

app.py

@@ -14,14 +14,14 @@ tokenizer = AutoTokenizer.from_pretrained(model_name)
 @spaces.GPU
 def generate(prompt):
     text = tokenizer.apply_chat_template(
-        messages,
+        prompt,
         tokenize=False,
         add_generation_prompt=True
     )
     model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
     generated_ids = model.generate(
         **model_inputs,
-        max_new_tokens=512,
+        max_new_tokens=2048,
     )
     generated_ids = [
         output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)