Added HF token for downloading Llama model

app.py

@@ -9,7 +9,11 @@ device = 'cuda' if torch.cuda.is_available() else 'cpu'
 
 @st.cache_resource
 def load_model():
-    return AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16).to(device)
+    return AutoModelForCausalLM.from_pretrained(
+        model_name,
+        torch_dtype=torch.bfloat16,
+        token=st.secrets['hf_token']
+    ).to(device)
 
 @st.cache_resource
 def load_tokenizer():