LLM Latent Adversarial Training

community

https://github.com/aengusl/latent-adversarial-training

AI & ML interests

None defined yet.

LLM-LAT 's datasets 2

LLM-LAT/benign-dataset

Viewer • Updated Jul 24, 2024 • 165k • 154 • 4

LLM-LAT/harmful-dataset

Viewer • Updated Jul 24, 2024 • 4.95k • 4.04k • 38