Update app.py

app.py

@@ -2,7 +2,7 @@ import gradio as gr
 from llama_cpp import Llama
 
 llm = Llama(
-    model_path="yugogpt-q4_0.gguf",
+    model_path="yugogpt-q4_k_s.gguf",
     n_ctx=4096,            # Doubled context length
     n_threads=8,           # Increased threads
     n_batch=1024,          # Increased batch size