Update app.py

app.py

@@ -4,7 +4,7 @@ import gradio as gr
 # from llama_cpp import Llama
 from langchain.llms import llamacpp
 from huggingface_hub import login, hf_hub_download
-from dotenv import load_dotenv, find_dotenv
+# from dotenv import load_dotenv, find_dotenv
 
 MODEL_ID = "TheBloke/Llama-2-7b-Chat-GGUF" 
 MODEL_BASENAME = "llama-2-7b-chat.Q4_K_M.gguf"
@@ -13,7 +13,8 @@ MODEL_BASENAME = "llama-2-7b-chat.Q4_K_M.gguf"
 CONTEXT_WINDOW_SIZE = 8000
 MAX_NEW_TOKENS = 2000
 N_BATCH = 128
-load_dotenv(find_dotenv(hf_token))
+
+os.getenv("hf_token")
 def load_quantized_model(model_id, model_basename):
     try:
         model_path = hf_hub_download(