Update README.md

README.md

@@ -40,7 +40,7 @@ model_id = "microsoft/Phi-4-mini-instruct"
 from torchao.quantization import Float8DynamicActivationFloat8WeightConfig, PerRow
 quant_config = Float8DynamicActivationFloat8WeightConfig(granularity=PerRow())
 quantization_config = TorchAoConfig(quant_type=quant_config)
-quantized_model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", quantization_config=quantization_config)
+quantized_model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", torch_dtype=torch.bfloat16, quantization_config=quantization_config)
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 
 # Push to hub