search

dmlc / gluon-nlp

NLP made easy
https://nlp.gluon.ai/
Apache License 2.0
2.56k stars 538 forks source link

Quantize QuestionAnswering models #1581

Open bgawrych opened 2 years ago

bgawrych commented 2 years ago

Description

This PR enables quantization on question answering scripts. Added custom calibration collector to avoid significant accuracy drop

github-actions[bot] commented 2 years ago

The documentation website for preview: http://gluon-nlp-staging.s3-accelerate.dualstack.amazonaws.com/PR1581/bc9ce0f899079a3cf1a8d80bbb1fb746dd3c69b5/index.html

github-actions[bot] commented 2 years ago

The documentation website for preview: http://gluon-nlp-staging.s3-accelerate.dualstack.amazonaws.com/PR1581/bba1525cc4ac848aca3ed452dbc15f43d8e53afb/index.html

github-actions[bot] commented 2 years ago

The documentation website for preview: http://gluon-nlp-staging.s3-accelerate.dualstack.amazonaws.com/PR1581/f2b5043608cbc68c0b67fbdcf2a3a3ef85363921/index.html