Update app.py

app.py

@@ -1,4 +1,7 @@
 from tqdm import tqdm
+from langchain_huggingface.llms import HuggingFaceEndpoint as HF
+
+llm = HF(repo_id="HuggingFaceH4/zephyr-7b-beta")
 from subprocess import Popen, PIPE as P
 #b=Popen("wget 1https://huggingface.co/peterpeter8585/deepseek-llm-7b-chat-Q8_0-GGUF/resolve/main/deepseek-llm-7b-chat-q8_0.gguf -O ./model.gguf",shell=True,stderr=P,stdout=P)
 #print(b.stdout.read()+b.stderr.read())
@@ -76,12 +79,7 @@ import multiprocessing
 #from langchain.llms import GPT4All
 
 #llm = GPT4All(model=("./model.gguf"))
-from langchain_huggingface.llms import HuggingFacePipeline
 
-llm = HuggingFacePipeline.from_model_id(
-    model_id="HuggingFaceH4/zephyr-7b-beta",
-    task="text-generation"
-)
 from langchain.retrievers import WikipediaRetriever as Wiki
 import gradio as gr
 chatbot = gr.Chatbot(