How to accelerate transformer with ANN?

marian-nmt / marian-examples

Examples, tutorials and use cases for Marian, including our WMT-2017/18 baselines.

Other

78 stars 34 forks source link

Closed PromptExpert closed 6 years ago

PromptExpert commented 6 years ago

How to enable averaging attention networks?

emjotde commented 6 years ago

Oh sorry, I didn't see your issue here. If you are still interested, the option is

--transformer-decoder-autoreg average-attention