Update app.py

app.py

@@ -8,7 +8,7 @@ config.config.stop = ["\n"]
 
 # path_to_llm = os.path.abspath("llama-2-7b-chat.ggmlv3.q4_1.bin")
 
-llm = ctransformers.AutoModelForCausalLM.from_pretrained("TheBloke/Llama-2-7b-Chat-GGUF", model_file="llama-2-7b-chat.q4_K_M.gguf", config=config)
+llm = ctransformers.AutoModelForCausalLM.from_pretrained("TheBloke/Llama-2-7b-Chat-GGUF", model_file="llama-2-7b-chat.Q4_K_M.gguf", config=config)
 
 def complete(prompt, stop=["User", "Assistant"]):
   tokens = llm.tokenize(prompt)