h = (scores @ v).transpose(1, 2).contiguous() RuntimeError: CUDA error: out of memory

dhlee347 / pytorchic-bert

Pytorch Implementation of Google BERT

Apache License 2.0

591 stars 179 forks source link

Closed leerelive closed 5 years ago

leerelive commented 5 years ago

i have this problem

dhlee347 commented 5 years ago

You might need to decrease your batch size to fit your GPU memory.