Update app.py

app.py

@@ -15,7 +15,7 @@ def invoke(input_text, model, tokenizer):
 
     prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)   
     inputs = tokenizer(prompt, return_tensors='pt', padding=True, truncation=True)
-    outputs = model.generate(**inputs, max_new_tokens=1200, num_return_sequences=1)
+    outputs = model.generate(**inputs, max_new_tokens=500, num_return_sequences=1)
 
     text = tokenizer.decode(outputs[0], skip_special_tokens=True)
     text = text.split("assistant")[1]