Download Latest Version Texar v0.2.4.zip (991.3 kB)
Email in envelope

Get an email when there's a new version of Texar

Home / v0.2.1
Name Modified Size InfoDownloads / Week
Parent folder
README.md 2019-07-17 2.3 kB
0
Texar v0.2.1.tar.gz 2019-07-17 532.4 kB
0
Texar v0.2.1.zip 2019-07-17 770.9 kB
0
Totals: 3 Items   1.3 MB 0

New features

  • Add support for GPT-2 345M model in examples/gpt-2. (#156)
  • Add BERT modules, including texar.modules.BERTEncoder (doc) and texar.modules.BERTClassifier (doc). (#167)

Feature improvements

  • Refactor TransformerEncoder and TransformerDecoder to separate position embeddings from the modules. (#126)
  • Allow passing a Tensor to output_layer of decoders' constructors -- used for weight tie b/w the output layer and input embedding matrix. (#126)
  • TransformerDecoder constructor interface made exact the same with RNN decoders constructor interfaces. (#126)
  • Refactor decoder Helpers to allow two-argument embedding_fn (supporting for position embedding). (#126)
  • Refactor SinusoidsPositionEmbedder to enable infinite large or negative position indexes. (#176)

Fixes

  • Fix texar.losses.reduce_batch_time when sequence has dtype other than tf.float32. (#143)
  • Fix texar.losses.reduce_dimensions when average_axes or sum_axes is int. (#141)
  • Fix GPT-2 tokenization loading path. (#165)
  • Fix examples/vae_text EOS bug. (#168)
  • Fix transformer bleu_tool.py (github.com) when translation_length is 0. (#176)
  • Fix StochasticConnector and ReparameterizedStochasticConnector when transform=False. (#179)
Source: README.md, updated 2019-07-17