Update app.py

app.py

@@ -30,14 +30,14 @@ MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
 device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
 
 #model_id = "nltpt/Llama-3.2-3B-Instruct"
-tokenizer = AutoTokenizer.from_pretrained(model_id)
+tokenizer = AutoTokenizer.from_pretrained(model_id,token=access_token)
 tokenizer.padding_side = 'right'
 tokenizer.pad_token = tokenizer.eos_token
 model = AutoModelForCausalLM.from_pretrained(
     model_id,
     device_map=device,
     torch_dtype=torch.bfloat16,
-    local_files_only = True
+    token=access_token
 )
 model.eval()