fairseq/docs
Myle Ott df2f84ce61 v0.8.0 -> v0.9.0 (#1452)
Summary:
Possibly breaking changes:
- Set global numpy seed (4a7cd58)
- Split `in_proj_weight` into separate k, v, q projections in MultiheadAttention (fdf4c3e)
- TransformerEncoder returns namedtuples instead of dict (27568a7)

New features:
- Add `--fast-stat-sync` option (e1ba32a)
- Add `--empty-cache-freq` option (315c463)
- Support criterions with parameters (ba5f829)

New papers:
- Simple and Effective Noisy Channel Modeling for Neural Machine Translation (49177c9)
- Levenshtein Transformer (86857a5, ...)
- Cross+Self-Attention for Transformer Models (4ac2c5f)
- Jointly Learning to Align and Translate with Transformer Models (1c66792)
- Reducing Transformer Depth on Demand with Structured Dropout (dabbef4)
- Unsupervised Cross-lingual Representation Learning at Scale (XLM-RoBERTa) (e23e5ea)
- BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension (a92bcda)
- CamemBERT: a French BERT (b31849a)

Speed improvements:
- Add CUDA kernels for LightConv and DynamicConv (f840564)
- Cythonization of various dataloading components (4fc3953, ...)
- Don't project mask tokens for MLM training (718677e)
Pull Request resolved: https://github.com/pytorch/fairseq/pull/1452

Differential Revision: D18798409

Pulled By: myleott

fbshipit-source-id: 860a0d5aaf7377c8c9bd63cdb3b33d464f0e1727
2019-12-03 15:19:33 -08:00
..
_static Add documentation 2018-09-03 19:15:23 -04:00
command_line_tools.rst Add fairseq to PyPI (#495) 2019-02-08 22:03:29 -08:00
conf.py v0.8.0 -> v0.9.0 (#1452) 2019-12-03 15:19:33 -08:00
criterions.rst Merge internal changes (#283) 2019-01-04 20:03:19 -08:00
data.rst Miscellaneous documentation improvements: (#868) 2019-09-23 12:27:12 -07:00
docutils.conf Add documentation 2018-09-03 19:15:23 -04:00
getting_started.rst Fix changes of file locations of subword-nmt (#1219) 2019-11-07 09:08:29 -08:00
index.rst Add documentation 2018-09-03 19:15:23 -04:00
lr_scheduler.rst Add fairseq to PyPI (#495) 2019-02-08 22:03:29 -08:00
make.bat Add documentation 2018-09-03 19:15:23 -04:00
Makefile Add documentation 2018-09-03 19:15:23 -04:00
models.rst Updates to model API (#561) 2019-05-15 07:12:41 -07:00
modules.rst Updates to model API (#561) 2019-05-15 07:12:41 -07:00
optim.rst Merge internal changes (#654) 2019-04-29 19:50:58 -07:00
overview.rst Updates to model API (#561) 2019-05-15 07:12:41 -07:00
requirements.txt Update documentation 2018-09-03 20:03:37 -04:00
tasks.rst Add documentation 2018-09-03 19:15:23 -04:00
tutorial_classifying_names.rst Standardize on 'teacher forcing' rather than 'input feeding' which is… (#769) 2019-07-25 07:24:07 -07:00
tutorial_simple_lstm.rst Standardize on 'teacher forcing' rather than 'input feeding' which is… (#769) 2019-07-25 07:24:07 -07:00