updated

app.py

@@ -7,7 +7,7 @@ from diffusers import DiffusionPipeline
 import torch
 from transformers import pipeline
 
-pipe = pipeline("text-generation", "meta-llama/Meta-Llama-3-8B-Instruct", torch_dtype=torch.bfloat16, device_map="auto")
+pipe = pipeline("text-generation", "meta-llama/Meta-Llama-3-8B-Instruct", torch_dtype=torch.bfloat16, device_map="auto"i, use_auth_token=True)
 response = pipe(chat, max_new_tokens=512)
 
 pipe.to('cuda')