Update app.py

app.py

@@ -2,18 +2,20 @@ import gradio as gr
 import numpy as np
 import onnxruntime as ort
 from transformers import AutoTokenizer, AutoModelForCausalLM
-from huggingface_hub import hf_hub_download
 import torch
+from huggingface_hub import hf_hub_download, HfFolder
+
+token = HfFolder.get_token() or os.getenv("HF_TOKEN")
 
 HF_MODEL_ID = "mistralai/Mistral-Nemo-Instruct-2407"
 HF_ONNX_REPO = "techAInewb/mistral-nemo-2407-fp32"
 ONNX_MODEL_FILE = "model.onnx"
 
 # Load tokenizer
-tokenizer = AutoTokenizer.from_pretrained(HF_MODEL_ID)
+tokenizer = AutoTokenizer.from_pretrained(HF_MODEL_ID, token=token)
 
 # Load PyTorch model
-pt_model = AutoModelForCausalLM.from_pretrained(HF_MODEL_ID, torch_dtype=torch.float32)
+pt_model = AutoModelForCausalLM.from_pretrained(HF_MODEL_ID, torch_dtype=torch.float32, token=token)
 pt_model.eval()
 
 # Load ONNX model