Example notebook showcasing a Captum-based method for interpreting transformer classifications
Below is an example (in black and white, for academic publication) using RoBERTa to classify polarizing rhetoric in political tweets.
-
Notifications
You must be signed in to change notification settings - Fork 0
Example notebook showcasing a method for interpreting transformer classifications
License
ssdorsey/transformers-interp
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
Example notebook showcasing a method for interpreting transformer classifications
Resources
License
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published