This release updates how the Learning Interpretability Tool (LIT) can be deployed on Google Cloud. You can now use LIT to interpret foundation models—including Gemini, Gemma, Llama, and Mistral—using LIT's prompt debugging workflows. LIT now provides public container images to make it easier to deploy on your hosting platform of choice, with an updated tutorial for deploying LIT with Cloud Run.
New Stuff
- LIT on GCP -
1075325,
1acc868,
55bfc99,
180f68a,
64114d5,
2488aa7,
9baac29,
60bdc7c,
7681476,
4c81182,
4e5e8e2,
b9a0b82,
424adce,
1d019c7,
f4436a2,
Non-breaking Changes, Bug Fixes, and Enhancements
- Upgrade LIT to MobX v6. - c1f5055
- Fix indexing issue in Sequence Salience module. - 58b1d2
- Load multiple model wrappers with shared model. - ba4d975
- Add the custom model and dataset loaders to prompt debugging notebook. - 338c6b
- Convert hosted demos images to multi-stage builds. - 4bf1f8
- Adding testing instructions to README. - f24b841
- More LIT documentation updates. - 2e9d267