Added ALBERT v2 quantization with INC example

dmlc / gluon-nlp

NLP made easy

https://nlp.gluon.ai/

Apache License 2.0

2.56k stars 538 forks source link

Added ALBERT v2 quantization with INC example #1591

Closed DominikaJedynak closed 1 year ago

DominikaJedynak commented 2 years ago

Description

This PR adds an example of quantizing ALBERT base v2 model with the Intel Neural Compressor with a custom strategy. Script run_squad_albert.py is based on the run_squad.py file. This change is based on this PR.