Skip to content

Instantly share code, notes, and snippets.

@prrao87

prrao87/quantize_fasttext.py

Created August 31, 2019 01:19
Show Gist options
  • Save prrao87/fe97da7b18f8937f63dab94a481e832b to your computer and use it in GitHub Desktop.
Save prrao87/fe97da7b18f8937f63dab94a481e832b to your computer and use it in GitHub Desktop.
Download ZIP
Raw
quantize_fasttext.py
# Quantize model to reduce space usage
model.quantize(input=train, qnorm=True, retrain=True, cutoff=100000)
model.save_model(os.path.join(model_path, "sst-5.ftz"))
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment