Update app.py

app.py

@@ -5,8 +5,11 @@ import gradio as gr
 from transformers import AutoModelForCausalLM, AutoTokenizer
 from huggingface_hub import snapshot_download
 from dotenv import load_dotenv
+import os
+token_hf = os.getenv('HF_TOKEN')
 load_dotenv()
 
+
 # Check if CUDA is available
 device = "cuda" if torch.cuda.is_available() else "cpu"
 
@@ -38,9 +41,9 @@ snapshot_download(
     ]
 )
 
-model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16)
+model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, token=token_hf)
 model.to(device)
-tokenizer = AutoTokenizer.from_pretrained(model_name)
+tokenizer = AutoTokenizer.from_pretrained(model_name, token_hf)
 print(f"Orpheus model loaded to {device}")
 
 # Process text prompt