Update app.py

app.py

@@ -2,9 +2,11 @@ import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM, TextStreamer, GenerationConfig, BitsAndBytesConfig
 import gradio as gr
 import os
-
+from huggingface_hub import login
 # Authenticate using token from environment
 hf_token = os.getenv("HF_TOKEN")
+login(token=hf_token)
+
 
 # Use quantization for low-memory GPU inference
 quantization_config = BitsAndBytesConfig(