A ground-up evaluation library that is designed for any model inference function that accepts tokens and outputs logits. Useful for evaluating a variety of types of interventions on a model with maximum flexibility.
Task
forked from magikarp01/tasks
-
Notifications
You must be signed in to change notification settings - Fork 0
aengusl/tasks-goose
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
My own set of general evaluations to be shared between projects
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published
Languages
- Jupyter Notebook 84.9%
- Python 15.1%