Update app.py

app.py

@@ -41,6 +41,7 @@ def load_model():
     device_map = accelerate.infer_auto_device_map(fake_model)
     model = transformers.LlamaForCausalLM.from_pretrained(
         repo_id,
+        device_map="auto"
         load_in_8bit=True,
         cache_dir="./cache",
     )