Update app.py

app.py

@@ -1,7 +1,7 @@
 import gradio as gr
 from llama_cpp import Llama
 
-llm = Llama(model_path="ggml-alpaca-7b-q4.bin")
+llm = Llama(model_path="ggml-alpaca-7b-q4.bin", n_ctx=256, n_batch=128)
 
 def generate_text(input_text):
     output = llm(f"{input_text}", max_tokens=128, stop=["Q:", "\n", "#"], echo=False)