Hou Lu

icon indicating a website link https://houlu369.github.io/ icon indicating an email [email protected]

icon company HKUST icon location Hong Kong icon location machine learning, deep learning

Results 1 comments of Hou Lu

Difference between paper and source code in training DynaBERT

The released code uses the width-adaptive teacher assistant at its largest width and depth (DynaBERTw, width_mult=1, depth_mult=1) as the teacher model. You can also use (DynaBERTw, width_mult, depth_mult=1) by inserting...