Update app.py

app.py

@@ -44,8 +44,8 @@ vectorstore = Milvus(connection_args=connection_args, collection_name=collection
 
 #downloading the model
 
-url = "https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGML/blob/main/llama-2-7b-chat.ggmlv3.q4_K_S.bin"
-output_file = "llama-2-7b-chat.ggmlv3.q4_K_S.bin"  # The filename you want to save the downloaded file as
+url = "https://huggingface.co/TheBloke/Llama-2-7b-Chat-GGUF/resolve/main/llama-2-7b-chat.Q5_K_M.gguf"
+output_file = "llama-2-7b-chat.Q5_K_M.gguf" # The filename you want to save the downloaded file as
 
 response = requests.get(url)
 
@@ -192,7 +192,7 @@ def stream(input_text,prompt,context1,context2) -> Generator:
     # Initialize the LLM we'll be using
     
     llm = LlamaCpp(
-        model_path="llama-2-7b-chat.ggmlv3.q4_K_S.bin",    #  model path
+        model_path="llama-2-7b-chat.Q5_K_M.gguf",    #  model path
         callbacks=[QueueCallback(q)],
         verbose=True,
         n_ctx=4000,