Update app.py

app.py

@@ -1,6 +1,7 @@
 import gradio as gr
 from transformers import AutoModelForCausalLM, AutoTokenizer
 import torch
+import os
 
 title = "# 🙋🏻‍♂️Tonic's ✒️InkubaLM-0.4B"
 description = """✒️InkubaLM has been trained from scratch using 1.9 billion tokens of data for five African languages, along with English and French data, totaling 2.4 billion tokens of data.  It is capable of understanding and generating content in five African languages: Swahili, Yoruba, Hausa, isiZulu, and isiXhosa, as well as English and French. 
@@ -8,10 +9,11 @@ description = """✒️InkubaLM has been trained from scratch using 1.9 billion
 🌟TeamTonic🌟 is always making cool demos! Join our active builder's 🛠️community 👻 [![Join us on Discord](https://img.shields.io/discord/1109943800132010065?label=Discord&logo=discord&style=flat-square)](https://discord.gg/GWpVpekp) On 🤗Huggingface:[MultiTransformer](https://huggingface.co/MultiTransformer) On 🌐Github: [Tonic-AI](https://github.com/tonic-ai) & contribute to🌟 [Build Tonic](https://git.tonic-ai.com/contribute)🤗Big thanks to Yuvi Sharma and all the folks at huggingface for the community grant 🤗
 """
 
+hf_token = os.getenv("HF_TOKEN")
 # Load the model and tokenizer
 model_name = "lelapa/InkubaLM-0.4B"
-model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True)
-tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True, use_auth_token=hf_token)
+tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True, use_auth_token=hf_token)
 
 # Move model to GPU if available
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")