Open flieks opened 4 years ago
Someone experience with deploying this to serverless ? AWS lambda has size restrictions to max of 512MB temp storage which is a problem.
Other options ? Because BERT can be GPU resource heavy if running fulltime
Hi. Also researching this. Found out that you can rather decrease the model requirements (aka use distilbert instead), or provision this yourself, try using cortex framework to ease the pain.
Someone experience with deploying this to serverless ? AWS lambda has size restrictions to max of 512MB temp storage which is a problem.
Other options ? Because BERT can be GPU resource heavy if running fulltime