New
v0.22.0
What's Changed
- Bump on-headers and compression in /tokenizers/examples/unstable_wasm/www by @dependabot[bot] in https://github.com/huggingface/tokenizers/pull/1827
- Implement
from_bytesandread_bytesMethods in WordPiece Tokenizer for WebAssembly Compatibility by @sondalex in https://github.com/huggingface/tokenizers/pull/1758 - fix: use AHashMap to fix compile error by @b00f in https://github.com/huggingface/tokenizers/pull/1840
- New stream by @ArthurZucker in https://github.com/huggingface/tokenizers/pull/1856
- [docs] Add more decoders by @pcuenca in https://github.com/huggingface/tokenizers/pull/1849
- Fix missing parenthesis in
EncodingVisualizer.calculate_label_colorsby @Liam-DeVoe in https://github.com/huggingface/tokenizers/pull/1853 - Update quicktour.mdx re: Issue #1625 by @WilliamPLaCroix in https://github.com/huggingface/tokenizers/pull/1846
- remove stray comment by @sanderland in https://github.com/huggingface/tokenizers/pull/1831
- Fix typo in README by @aisk in https://github.com/huggingface/tokenizers/pull/1808
- RUSTSEC-2024-0436 - replace paste with pastey by @nystromjd in https://github.com/huggingface/tokenizers/pull/1834
- Tokenizer: Add native async bindings, via py03-async-runtimes. by @michaelfeil in https://github.com/huggingface/tokenizers/pull/1843
New Contributors
- @b00f made their first contribution in https://github.com/huggingface/tokenizers/pull/1840
- @pcuenca made their first contribution in https://github.com/huggingface/tokenizers/pull/1849
- @Liam-DeVoe made their first contribution in https://github.com/huggingface/tokenizers/pull/1853
- @WilliamPLaCroix made their first contribution in https://github.com/huggingface/tokenizers/pull/1846
- @sanderland made their first contribution in https://github.com/huggingface/tokenizers/pull/1831
- @aisk made their first contribution in https://github.com/huggingface/tokenizers/pull/1808
- @nystromjd made their first contribution in https://github.com/huggingface/tokenizers/pull/1834
- @michaelfeil made their first contribution in https://github.com/huggingface/tokenizers/pull/1843
Full Changelog: https://github.com/huggingface/tokenizers/compare/v0.21.3...v0.22.0rc0