Update app.py

app.py

@@ -10,7 +10,7 @@ tokenizer = AutoTokenizer.from_pretrained(model_id)
 def chat(question):
     prompt = f"### Instruction: {question}\n### Response:"
     inputs = tokenizer(prompt, return_tensors="pt")
-    output = model.generate(inputs["input_ids"])
+    output = model.generate(inputs["input_ids"], max_new_tokens=100)
     response = tokenizer.decode(output[0].tolist())
     print(response)
     return response