Update app.py

app.py

@@ -88,17 +88,9 @@ else:
 #pipe=pipeline(model=m,tokenizer=t,task="text-generation")
 import multiprocessing
 
-from langchain_community.chat_models import ChatLlamaCpp
+from langchain_community.llms import GPT4ALL
 
-llm = ChatLlamaCpp(
-    temperature=0,
-    model_path="./llama-3-open-ko-8b-instruct-preview-q5_k_m.gguf",
-    n_ctx=10000,
-    n_batch=300,  # Should be between 1 and n_ctx, consider the amount of VRAM in your GPU.
-    n_threads=multiprocessing.cpu_count() - 1,
-    repeat_penalty=1.5,
-    top_p=0.5,
-)
+llm = GPT4ALL(model=("./llama-3-open-ko-8b-instruct-preview-q5_k_m.gguf"))
 from langchain.retrievers import WikipediaRetriever as Wiki
 import gradio as gr
 chatbot = gr.Chatbot(