Does MQBench supports Advanced PTQ on the transformer model?
hobbitlzy opened this issue · 3 comments
hobbitlzy commented
The transformer model seems not to support layer-wisely finetuning on the calibration dataset. Will this feature be supported?
Tracin commented
hobbitlzy commented
I'm sorry I didn't make it clear. Can the transformer model be finetuned using the AdaRound-like algorithm?
github-actions commented
This issue has not received any updates in 120 days. Please reply to this issue if this still unresolved!