PTQ-Level Efficiency, QAT-Level Accuracy | 训练后量化的效率,量化感知训练的精度
fixed typo
wenhuach213c58c7910a72
diff --git a/README.md b/README.mdindex 28c8f91a5..fc97260ba 100644--- a/README.md+++ b/README.md@@ -25,9 +25,9 @@ scheme = "asym"autoround = AutoRound(model, tokenizer, bits=4, group_size=128, scheme=scheme)autoround.quantize()-### export to intel-extension-for-transformers for intel cpu deployment+output_dir = "/PATH/TO/SAVE/COMPRESSED/MODEL/"-autoround.export(output_dir=output_dir)+autoround.export(output_dir)##inference## pip install intel-extension-for-transformers (for now, please install from source)