undefined | Better HN

0 pointsramoz2y ago0 comments

I’ve also ran models in Go, transformers even T5. There wasn’t that much overhead maybe some annoying compilation stuff but nothing crazy.

This was tensorflow btw which has Go bindings support.

It is a smart & worthwhile move, we also needed to drop python for performance/cost gains.

0 comments

eh, awesome! Seems this one, right? https://github.com/galeone/tfgo. Quite many stars.

ramozOP2y ago

Actually the docs around this weren’t great. Took the train-in-python & inference-in-go approach. And only for versions greater than tf2

Write a blog post then about this! I can tell you it is hardly a solved problem.

j / k navigate · click thread line to collapse

eh, awesome! Seems this one, right? https://github.com/galeone/tfgo. Quite many stars.

ramozOP2y ago

Actually the docs around this weren’t great. Took the train-in-python & inference-in-go approach. And only for versions greater than tf2

Write a blog post then about this! I can tell you it is hardly a solved problem.

j / k navigate · click thread line to collapse