EuroSafeAI
/

EuroSafeGuard-v1

Text Classification

constitutional-classifiers

jailbreak-detection

content-moderation

Model card Files Files and versions

EuroSafeGuard-v1

684 MB

Ctrl+K

Ctrl+K

1 contributor

History: 14 commits

samuelsimko's picture

Link the paper as guard.safe.eu/paper

775fdf8 verified 2 days ago

assets
Add bars.png 2 days ago
exchange
EuroSafeGuard v1: probe, 5 input-classifier seeds, exchange classifier, thresholds, loader, model card 6 days ago
gate
EuroSafeGuard v1: probe, 5 input-classifier seeds, exchange classifier, thresholds, loader, model card 6 days ago
probe
EuroSafeGuard v1: probe, 5 input-classifier seeds, exchange classifier, thresholds, loader, model card 6 days ago
thresholds
Add full mode (paper's end-to-end configuration) and its per-seed thresholds; fix model card; remove __pycache__ 4 days ago
.gitattributes

2 kB
Add bars.png 2 days ago
README.md

5.99 kB
Link the paper as guard.safe.eu/paper 2 days ago
eurosafeguard.py

15.8 kB
v1 release: rename to -v1, simpler card 2 days ago
taxonomy_11heads_short.json

5.69 kB
EuroSafeGuard v1: probe, 5 input-classifier seeds, exchange classifier, thresholds, loader, model card 6 days ago