requirements.txt

1 llama-cpp-python==0.1.62
2

app.py

@@ -26,7 +26,7 @@ llm = Llama(model_path=filename, n_ctx=512, n_batch=126)
 def generate_text(prompt="Who is the CEO of Apple?"):
     output = llm(
         prompt,
-        max_tokens=256,
+        max_tokens=2000,
         temperature=0.1,
         top_p=0.5,
         echo=False,
@@ -57,4 +57,4 @@ gradio_interface = gr.Interface(
     examples=examples,
     title="Vicuna-7B",
 )
-gradio_interface.launch()
+gradio_interface.launch()