Update app.py

app.py

@@ -2,6 +2,7 @@ import gradio as gr
 from transformers import pipeline, TextIteratorStreamer
 from threading import Thread
 import torch
+import os
 import subprocess
 import spaces
 import os
@@ -60,7 +61,7 @@ Below this is the role you are to play.
 # Install flash-attn
 subprocess.run('pip install flash-attn --no-build-isolation', env={'FLASH_ATTENTION_SKIP_CUDA_BUILD': "TRUE"}, shell=True)
 # Initialize the model pipeline
-generator = pipeline('text-generation', model='Locutusque/Open-Thespis-Llama-3B', torch_dtype=torch.bfloat16)
+generator = pipeline('text-generation', model='Locutusque/Open-Thespis-Llama-3B', torch_dtype=torch.bfloat16, token=os.getenv("TOKEN"))
 @spaces.GPU
 def generate_text(prompt, system_prompt, temperature, top_p, top_k, repetition_penalty, max_length):
     """