PTQ-Level Efficiency, QAT-Level Accuracy | 训练后量化的效率,量化感知训练的精度
tiny change
wenhuach21e0cf621c86b6
diff --git a/README.md b/README.mdindex 9d9749220..34c69e1d7 100644--- a/README.md+++ b/README.md@@ -74,7 +74,7 @@ ChatGlm-V1 is not supported## Validated Models-For wikitext2/ptb-new/c4-new ppl, we follow the code of gptq and set the seqence length to 2048. For lm-eval wikitext ppl, we adopt lm-eval.+For wikitext2/ptb-new/c4-new ppl, we follow the code of gptq and set the sequence length to 2048. For lm-eval wikitext ppl, we adopt lm-eval. The quantization configure is W4G128.<table border="1"><tr>