Update src/streamlit_app.py

src/streamlit_app.py

@@ -29,8 +29,9 @@ device = torch.device("cpu")
 @st.cache_resource
 def load_model(model_name: str = "meta-llama/Llama-3.2-1B"):
     """Load and cache the tokenizer and model."""
-    tokenizer = AutoTokenizer.from_pretrained(model_name)
-    model = AutoModelForCausalLM.from_pretrained(model_name)
+    token = os.environ.get("HF_TOKEN")
+    tokenizer = AutoTokenizer.from_pretrained(model_name, token=token)
+    model = AutoModelForCausalLM.from_pretrained(model_name, token=token)
     model = model.to(device)
     return tokenizer, model