Update README.md

README.md

@@ -20,12 +20,13 @@ from torchao.quantization import Int4WeightOnlyConfig
 quant_config = Int4WeightOnlyConfig(group_size=128)
 quantization_config = TorchAoConfig(quant_type=quant_config)
 quantized_model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", quantization_config=quantization_config)
+tokenizer = AutoTokenizer.from_pretrained(model_id)
 
 # Push to hub
 USER_ID = "YOUR_USER_ID"
 save_to = "{USER_ID}/{model_id}-int4wo"
 quantized_model.push_to_hub(save_to, safe_serialization=False)
-
+tokenizer.push_to_hub(save_to)
 
 # Manual Testing
 messages = [