-
Yih-Dar authored
* Remove hard-coded uses of float32 to fix mixed precision use in TF Distilbert * fix style * fix gelu dtype issue in TF Distilbert * fix numeric overflow while using half precision
a75e3198
* Remove hard-coded uses of float32 to fix mixed precision use in TF Distilbert * fix style * fix gelu dtype issue in TF Distilbert * fix numeric overflow while using half precision