Update app.py

app.py

@@ -4,13 +4,12 @@ from langchain_community.llms import CTransformers
 from langchain.chains import RetrievalQA
 import gradio as gr
 from huggingface_hub import hf_hub_download
-import os
 
 DB_FAISS_PATH = "vectorstores/db_faiss"
 
 def load_llm():
-    model_name = 'TheBloke/Llama-2-7B-Chat-GGML'  # Replace with the actual model repository name
-    model_path = hf_hub_download(repo_id=model_name, filename='pytorch_model.bin', cache_dir='./models')
+    model_name = 'TheBloke/Llama-2-7B-Chat-GGML'  # Correct model repository
+    model_path = hf_hub_download(repo_id=model_name, filename='llama-2-7b-chat.ggmlv3.q8_0.bin', cache_dir='./models')
     llm = CTransformers(
         model=model_path,
         model_type="llama",
@@ -76,3 +75,4 @@ iface = gr.Interface(
 
 iface.launch()
 
+