PTQ-Level Efficiency, QAT-Level Accuracy | 训练后量化的效率,量化感知训练的精度
update readme
wenhuach21cf5e1d395f13
diff --git a/README.md b/README.mdindex 8a5a00a3f..25715c420 100644--- a/README.md+++ b/README.md@@ -74,11 +74,6 @@ from auto_round import AutoRoundautoround = AutoRound(model, tokenizer, bits=bits, group_size=group_size, scheme=scheme,device="hpu", scale_dtype="bf16", amp=False)autoround.quantize()--# Intel CPU Inference, Currently, llama, bloom, and mistral are supported.-output_dir = "/path/to/quantized_model"-autoround.export(output_dir)-# then follow ITREX(https://github.com/intel/intel-extension-for-transformers/tree/main/intel_extension_for_transformers/llm/runtime/neural_speed) to load the model and do inference```