What's Changed
* Refactored exl2 method to add LoRA, 8bit cache, and other features supported by exllama by psych0v0yager in https://github.com/outlines-dev/outlines/pull/729
* Update the docstring of `exl2` by rlouf in https://github.com/outlines-dev/outlines/pull/742
* Added model_kwargs by isamu-isozaki in https://github.com/outlines-dev/outlines/pull/744
* Fix generation of multi-token unicode characters by ai-and-i in https://github.com/outlines-dev/outlines/pull/738
* Make `model_kwargs` dictionary by default by rlouf in https://github.com/outlines-dev/outlines/pull/747
* Check if the given token is a string by silverriver in https://github.com/outlines-dev/outlines/pull/745
* Add BibteX citation by rlouf in https://github.com/outlines-dev/outlines/pull/755
* fixed parsing token vocabularies for gemma and gpt-sw3 models by ai-and-i in https://github.com/outlines-dev/outlines/pull/763
* fix: Do not reset `RegexLogitsProcessor._fsm_state` by saattrupdan in https://github.com/outlines-dev/outlines/pull/760
New Contributors
* psych0v0yager made their first contribution in https://github.com/outlines-dev/outlines/pull/729
* ai-and-i made their first contribution in https://github.com/outlines-dev/outlines/pull/738
* silverriver made their first contribution in https://github.com/outlines-dev/outlines/pull/745
**Full Changelog**: https://github.com/outlines-dev/outlines/compare/0.0.36...0.0.37