diff --git a/bindings/python/CHANGELOG.md b/bindings/python/CHANGELOG.md index f39df23ac..091f94321 100644 --- a/bindings/python/CHANGELOG.md +++ b/bindings/python/CHANGELOG.md @@ -1,3 +1,10 @@ +# v0.5.2 + +## Fixes: +- We introduced a bug related to the saving of the WordPiece model in 0.5.2: The `vocab.txt` file was named +`vocab.json`. This is now fixed. +- The `WordLevel` model was also saving its vocabulary to the wrong format. + # v0.5.1 ## Changes: diff --git a/bindings/python/Cargo.lock b/bindings/python/Cargo.lock index 5f4e881ba..c1391ca59 100644 --- a/bindings/python/Cargo.lock +++ b/bindings/python/Cargo.lock @@ -572,7 +572,7 @@ dependencies = [ [[package]] name = "tokenizers-python" -version = "0.5.1" +version = "0.5.2" dependencies = [ "pyo3 0.8.4 (registry+https://github.com/rust-lang/crates.io-index)", "tokenizers 0.7.0", diff --git a/bindings/python/Cargo.toml b/bindings/python/Cargo.toml index 52b9d35c8..42414e9b8 100644 --- a/bindings/python/Cargo.toml +++ b/bindings/python/Cargo.toml @@ -1,6 +1,6 @@ [package] name = "tokenizers-python" -version = "0.5.1" +version = "0.5.2" authors = ["Anthony MOI "] edition = "2018" diff --git a/bindings/python/setup.py b/bindings/python/setup.py index 47a9b5473..2b305fdcb 100644 --- a/bindings/python/setup.py +++ b/bindings/python/setup.py @@ -3,7 +3,7 @@ setup( name="tokenizers", - version="0.5.1", + version="0.5.2", description="Fast and Customizable Tokenizers", long_description=open("README.md", "r", encoding="utf-8").read(), long_description_content_type="text/markdown", diff --git a/bindings/python/tokenizers/__init__.py b/bindings/python/tokenizers/__init__.py index 5282011a8..c23b69f2a 100644 --- a/bindings/python/tokenizers/__init__.py +++ b/bindings/python/tokenizers/__init__.py @@ -1,4 +1,4 @@ -__version__ = "0.5.1" +__version__ = "0.5.2" from .tokenizers import Tokenizer, Encoding from .tokenizers import decoders