Update app.py

app.py

@@ -1,5 +1,7 @@
 import torch
 import spaces
+import os
+HF_TOKEN = os.environ["HF_TOKEN"]
 from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
 from peft import LoraConfig, PeftModel, get_peft_model
 import gradio as gr
@@ -18,7 +20,8 @@ bnb_config = BitsAndBytesConfig(
 # Load base model with quantization (replace 'your-username' if needed)
 base_model = AutoModelForCausalLM.from_pretrained(
     "meta-llama/Meta-Llama-3-8B-Instruct", # Replace with actual base model
-    quantization_config=bnb_config, 
+    quantization_config=bnb_config,
+    hf_token=HF_TOKEN,
 )
 
 # Apply LoRA adapters