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
wenhuach21c70a209d8aa0
diff --git a/autoround/README.md b/autoround/README.mdindex 3146e4e53..95b5e59f6 100644--- a/autoround/README.md+++ b/autoround/README.md@@ -64,12 +64,12 @@ Auto Rounding may encounter random issues with Qwen models.ChatGlm-V1 is not supported## Validated Models+Mistral-7b doneLLaMAV1 doneLLaMAv2 doneLaMini-GPT-124M doneQWEN1-8B done,but has random issueOPT-125M done-Mistral-7b Smoke test doneBloom-560 smoke test donefalcon-7b smoke test donegpt-leo-125m smoke test done