trying gguf for cpu inf

app.py

@@ -1,11 +1,11 @@
 import gradio as gr
 from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
 
-model_name_or_path = "TheBloke/Llama-2-13B-chat-GPTQ"
+model_name_or_path = "TheBloke/Llama-2-13B-chat-GGUF"
 model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
                                              device_map="auto",
                                              trust_remote_code=False,
-                                             revision="gptq-4bit-32g-actorder_True")
+                                             revision="llama-2-13b-chat.Q4_K_M.gguf")
 
 tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)