Update app.py

app.py

@@ -105,7 +105,8 @@ def main():
         #token=token,
         #)
 
-        llm = CTransformers(model="TheBloke/Llama-2-7B-Chat-GGML/llama-2-7b-chat.ggmlv3.q4_0.bin",
+        llm = CTransformers(model="TheBloke/Llama-2-7B-Chat-GGML",
+                            model_file="llama-2-7b-chat.ggmlv3.q4_0.bin",
                             model_type="llama",
                             max_new_tokens=512,
                             temperature=0.1)