songheony commented 5 years ago

The pretrained vectors according to the official document[https://github.com/facebookresearch/fastText/blob/master/docs/pretrained-vectors.md] are in dimension 300.

We are publishing pre-trained word vectors for 294 languages, trained on Wikipedia using fastText. These vectors in dimension 300 were obtained using the skip-gram model described in Bojanowski et al. (2016) with default parameters.

Also in this implementation, FastText class return 100 dimension vectors.

codecov-io commented 5 years ago

Codecov Report

Merging #74 into master will not change coverage. The diff coverage is n/a.

@@           Coverage Diff           @@
##           master      #74   +/-   ##
=======================================
  Coverage   94.02%   94.02%           
=======================================
  Files          57       57           
  Lines        1524     1524           
=======================================
  Hits         1433     1433           
  Misses         91       91

Impacted Files	Coverage Δ
torchnlp/word_to_vector/fast_text.py	`100% <ø> (ø)`	:arrow_up:

Continue to review full report at Codecov.

Legend - Click here to learn more Δ = absolute <relative> (impact), ø = not affected, ? = missing data Powered by Codecov. Last update eb61fee...edaf2c0. Read the comment docs.

PetrochukM commented 5 years ago

This is great. Thank you for catching that!

PetrochukM / PyTorch-NLP

Fix: Doc for FastText #74

Codecov Report