What's Changed
- Correct mlx-lm example unpacking operator by @Anri-Lombard in #1786
- Remove todos by @Anri-Lombard in #1788
- fix: correct chat format usage by @Ki-Seki in #1790
- Add AsyncOllama to all exports by @Anri-Lombard in #1791
- fix: Best-effort use of chat completion by @Ki-Seki in #1789
- Fix bug in JsonSchema resulting in the schema validation not running by @RobinPicard in #1795
- Update the is_int_instance to exclude booleans by @RobinPicard in #1799
- Have the _handle_list function gives an explicit error if no args by @RobinPicard in #1801
- Initial lm studio integration by @Anri-Lombard in #1787
- Add sentencepiece to transformers optional dependencies by @majiayu000 in #1796
- Add a step in the GitHub actions to cache HF models by @RobinPicard in #1807
- Upgrade outlines_core and update imports by @RobinPicard in #1808
- Add a step to free disk space in the CI by @RobinPicard in #1804
- Fix typo in vision argument of Ollama by @RobinPicard in #1811
- Move from supported Python version from 3.9-3.12 to 3.10-3.13 by @RobinPicard in #1813
- Add architecture documentation to the Guide section by @majiayu000 in #1797
- Add parametrized Transformers smoke test for tokenizer robustness by @kudos07 in #1814
- Fix a bug in the Transformers tokenizer by @RobinPicard in #1817
New Contributors
- @Anri-Lombard made their first contribution in #1786
- @majiayu000 made their first contribution in #1796
- @kudos07 made their first contribution in #1814
Full Changelog: 1.2.9...1.2.10