Update app.py

app.py

@@ -4,7 +4,14 @@ from langchain.vectorstores import FAISS
 from langchain.llms import CTransformers
 from langchain.chains import RetrievalQA
 import gradio as gr
+from transformers import AutoTokenizer, AutoModelForCausalLM
+from huggingface_hub import hf_hub_download
 
+def load_model():
+    model_name = 'TheBloke/Llama-2-7B-Chat-GGML'
+    tokenizer = AutoTokenizer.from_pretrained(model_name)
+    model = AutoModelForCausalLM.from_pretrained(model_name)
+    return tokenizer, model
 DB_FAISS_PATH = "vectorstores/db_faiss"
 
 custom_prompt_template = """Use the following pieces of information to answer the user's question.
@@ -23,7 +30,7 @@ def set_custom_prompt():
 
 def load_llm():
     llm = CTransformers(
-        model="llama-2-7b-chat.ggmlv3.q8_0.bin",
+        model=model,
         model_type="llama",
         max_new_tokens=512,
         temperature=0.5