Update app.py

app.py

@@ -1,3 +1,4 @@
+import os
 import gradio as gr
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
@@ -5,8 +6,8 @@ from transformers import StoppingCriteria, StoppingCriteriaList, TextIteratorStr
 from threading import Thread
 
 # Loading the tokenizer and model from Hugging Face's model hub.
-tokenizer = AutoTokenizer.from_pretrained("soketlabs/pragna-1b")
-model = AutoModelForCausalLM.from_pretrained("soketlabs/pragna-1b")
+tokenizer = AutoTokenizer.from_pretrained("soketlabs/pragna-1b", token=os.environ.get('HF_TOKEN'))
+model = AutoModelForCausalLM.from_pretrained("soketlabs/pragna-1b", token=os.environ.get('HF_TOKEN'))
 
 # using CUDA for an optimal experience
 device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')