Update app.py

app.py

@@ -60,8 +60,13 @@ def predict(message, history, system_prompt, temperature, max_tokens):
 
 if __name__ == "__main__":
     args = parse_args()
-    tokenizer = AutoTokenizer.from_pretrained("stabilityai/stablelm-2-12b-chat", trust_remote_code=True)
-    model = AutoModelForCausalLM.from_pretrained("stabilityai/stablelm-2-12b-chat", trust_remote_code=True, torch_dtype=torch.bfloat16)
+    tokenizer = AutoTokenizer.from_pretrained("stabilityai/stablelm-2-12b-chat")
+    tokenizer = AutoTokenizer.from_pretrained('stabilityai/stablelm-2-12b-chat')
+    model = AutoModelForCausalLM.from_pretrained(
+        'stabilityai/stablelm-2-12b-chat',
+        torch_dtype=torch.bfloat16,
+        low_cpu_mem_usage=True
+    )
     device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
     model = model.to(device)
     gr.ChatInterface(