Update app.py

app.py

@@ -1,20 +1,21 @@
 import gradio as gr
 from llama_cpp import Llama
 
-llm = Llama.from_pretrained(
-    repo_id="operablepattern/gemma-2b-it-Q",
-    filename="*Q5_K_M.gguf",
-    chat_format="gemma",
-    max_tokens=32,
-    verbose=True
-)
-# except:
-#     llm = Llama(
-#         model_path="./gemma-2b-it-Q5_K_M.gguf",
-#         max_tokens=32,
-#         chat_format="gemma",
-#         verbose=True
-#     )
+try:
+    llm = Llama.from_pretrained(
+        repo_id="operablepattern/gemma-2b-it-Q",
+        filename="*Q5_K_M.gguf",
+        chat_format="gemma",
+        max_tokens=32,
+        verbose=True
+    )
+except:
+    llm = Llama(
+        model_path="./gemma-2b-it-Q5_K_M.gguf",
+        chat_format="gemma",
+        max_tokens=32,
+        verbose=True
+    )
 
 def response(message, history):
     print(message)