L

self.d_k = d_model // h gives 64 dimension ?

1

https://github.com/codertimo/BERT-pytorch/blob/d10dc4f9d5a6f2ca74380f62039526eb7277c671/bert_pytorch/model/attention/multi_head.py#L15 Looks that **self.d_k = d_model // h ---> embed size 768 dividing number of heads 12 = 64** ``` self.d_k = d_model // h # 64 self.h = h...