v2.16.0
What's Changed
- added conditional check for hugging face by @bryce13950 in #919
- created a seperate list of models to test for public PRs by @bryce13950 in #920
- added alternative when hf token is not included by @bryce13950 in #921
- shrunk loss test by @bryce13950 in #922
- Fix broken test, per issue #913 by @JasonBenn in #914
- Fix loading on specific device by @mntss in #906
- Add qwen3 by @mntss in #937
- Improve ActivationCache docs by @BorisTheBrave in #901
- Feature: Get the value for rotary base from the hugging face config, only for Qwen for now. by @Gusanidas in #887
- updated mypy by @bryce13950 in #940
- updated numpy dependency by @bryce13950 in #943
- upated torch by @bryce13950 in #942
- updated transformers by @bryce13950 in #939
- Fixed Qwen 3 docs issues by @bryce13950 in #946
New Contributors
- @JasonBenn made their first contribution in #914
- @BorisTheBrave made their first contribution in #901
- @Gusanidas made their first contribution in #887
Full Changelog: v2.15.4...v2.16.0