Update app.py

app.py

@@ -18,7 +18,7 @@ if not hf_token:
 # Load LLaMA-2 model with authentication
 llama_pipe = pipeline(
     "text-generation",
-    model="meta-llama/Llama-2-7b-chat-hf",
+    model="TheBloke/Llama-2-7B-Chat-GGUF",
     token=hf_token  # Pass the token explicitly
 )