Update app.py

app.py

@@ -5,7 +5,7 @@ llm = Llama(model_path="ggml-model-q4_0.bin", n_ctx=256, n_batch=128)
 
 def generate_text(input_text):
     print(input_text)
-    output = llm(f"### Instruction:\n{input_text}\n\n### Response:\n", max_tokens=512, echo=False)
+    output = llm(f"### Instruction:\n{input_text}\n\n### Response:\n", max_tokens=128, echo=False)
     print(output)
     return output['choices'][0]['text']