Update app.py

app.py

@@ -72,7 +72,11 @@ from langchain_core.callbacks.manager import CallbackManagerForLLMRun
 from langchain_core.callbacks.manager import AsyncCallbackManagerForLLMRun
 from langchain_core.runnables import run_in_executor
 from transformers import AutoTokenizer, AutoModelForCausalLM
-
+import requests
+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",stream=True)
+with open("llama-3-open-ko-8b-instruct-preview-q5_k_m.gguf","wb") as f:
+    for i in req.iter_content(10000000):
+        f.write(i)
 
 #from transformers import pipeline,AutoModelForCausalLM as M,AutoTokenizer as T
 #m=M.from_pretrained("peterpeter8585/syai4.3")