Update model.py

model.py

@@ -1,5 +1,9 @@
 import torch
 from transformers import pipeline
+import os 
+
+hf_token = os.getenv("LLM_token")
+os.environ["HUGGINGFACE_HUB_TOKEN"] = hf_token
 
 def load_model(model_path="meta-llama/Meta-Llama-3-8B-Instruct"):
     device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
@@ -9,5 +13,6 @@ def load_model(model_path="meta-llama/Meta-Llama-3-8B-Instruct"):
         model=model_path,
         model_kwargs={"torch_dtype": torch.float16} if torch.cuda.is_available() else {},
         device=device,
+        token=hf_token
     )
     return pipe