Update app.py

app.py

@@ -6,6 +6,7 @@ from PyPDF2 import PdfReader
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain.callbacks.manager import CallbackManager
 from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
+
 from langchain.vectorstores import Qdrant
 from qdrant_client.http import models
 from ctransformers import AutoModelForCausalLM
@@ -18,7 +19,7 @@ print("Embedding model loaded...")
 callback_manager = CallbackManager([StreamingStdOutCallbackHandler()])
 
 llm = AutoModelForCausalLM.from_pretrained(
-    "refuelai/Llama-3-Refueled",
+    "TheBloke/Llama-2-7B-Chat-GGUF",
     model_file="llama-2-7b-chat.Q3_K_S.gguf",
     model_type="llama",
     temperature=0.2,
@@ -28,6 +29,7 @@ llm = AutoModelForCausalLM.from_pretrained(
 
 print("LLM loaded...")
 
+
 def chat(files, question):
     def get_chunks(text):
         text_splitter = RecursiveCharacterTextSplitter(