PTQ-Level Efficiency, QAT-Level Accuracy | 训练后量化的效率,量化感知训练的精度
update norm bias tuning doc (#1155)
Wenhua Cheng6723ef0aec70
diff --git a/docs/tuning_norm_bias.md b/docs/tuning_norm_bias.mdindex 4281134bd..df312c503 100644--- a/docs/tuning_norm_bias.md+++ b/docs/tuning_norm_bias.md@@ -4,7 +4,9 @@**Personal view by Wenhua, welcome to discuss**-**Work in Progress**+**Performance is poor in most scenarios, so it is not recommended for use at this time.**++<div align="left">Recent studies have found that tuning LayerNorm and bias through optimizer like Adam can lead to better results, especially for low-bit quantization such as 2-bit. However, I personally do not favor the use of Adam for this purpose, as detailed in the following section, and introduce an alternative way, detailed in the last section.