Update app.py

app.py

@@ -67,12 +67,6 @@ from langchain_core.runnables import run_in_executor
 from transformers import AutoTokenizer, AutoModelForCausalLM
 import requests
 import os
-if os.path.exists("./llama-3-open-ko-8b-instruct-preview-q5_k_m.gguf"):
-    pass
-else:
-    req=requests.get("https://huggingface.co/peterpeter8585/Llama-3-Open-Ko-8B-Instruct-preview-Q5_K_M-GGUF/resolve/main/llama-3-open-ko-8b-instruct-preview-q5_k_m.gguf")
-    with open("./llama-3-open-ko-8b-instruct-preview-q5_k_m.gguf","wb") as f:
-        f.write(req.content)
 #from transformers import pipeline,AutoModelForCausalLM as M,AutoTokenizer as T
 #m=M.from_pretrained("peterpeter8585/syai4.3")
 #t=T.from_pretrained("peterpeter8585/syai4.3")
@@ -81,7 +75,7 @@ import multiprocessing
 
 from langchain.llms import GPT4All
 
-llm = GPT4All(model=("./llama-3-open-ko-8b-instruct-preview-q5_k_m.gguf"))
+llm = GPT4All(model=("./model.gguf"))
 from langchain.retrievers import WikipediaRetriever as Wiki
 import gradio as gr
 chatbot = gr.Chatbot(