Update app.py

app.py

@@ -110,7 +110,7 @@ model = AutoModelForCausalLM.from_pretrained(
 def conversation_predict(input_text):
     input_ids = tokenizer(input_text, return_tensors="pt")
     
-    outputs = model.generate(**input_ids)
+    outputs = model.generate(**input_ids, max_new_tokens = 2048)
 
     return tokenizer.decode(outputs[0])