Update app.py

app.py

@@ -38,7 +38,7 @@ device = f'cuda:{cuda.current_device()}' if cuda.is_available() else 'cpu'
 #     bnb_4bit_compute_dtype=bfloat16
 # )
 
-tokenizer = AutoTokenizer.from_pretrained("meta-llama/Meta-Llama-3-8B-Instruct")
+tokenizer = AutoTokenizer.from_pretrained("meta-llama/Meta-Llama-3-8B-Instruct",token=HF_TOKEN)
 model = AutoModelForCausalLM.from_pretrained("meta-llama/Meta-Llama-3-8B-Instruct", device_map="auto")  # to("cuda:0") 
 terminators = [
     tokenizer.eos_token_id,