mlboydaisuke
/

Shieldstral-CoreAI

Text Classification

Model card Files Files and versions

Shieldstral-CoreAI / README.md

Commit History

Card: macOS/iOS 27 GA wording (beta requirement dropped; beta findings dated)

57aa14e
verified

mlboydaisuke commited on 4 days ago

Card: DeviceMark row (2026-09)

4c19d4d
verified

mlboydaisuke commited on 12 days ago

Card metadata: library_name coreai, ensure coreai tag

c1d394c
verified

mlboydaisuke commited on 12 days ago

Card: definition line (Core AI, 2026-09)

1e5c625
verified

mlboydaisuke commited on 14 days ago

Card: base_model_relation: quantized (so the conversion lists under the base model's Quantizations, not Finetunes)

c2395f3
verified

mlboydaisuke commited on 15 days ago

Shieldstral-1.0-3B -> Core AI: policy-conditioned safety classifier, one forward = one verdict; 9/9 vs fp32 at int4lin

777ac29
verified

mlboydaisuke commited on Aug 16

Link the card back to its collection and the request box

602832c
verified

mlboydaisuke commited on Aug 15

card: Swift usage via coreai-kit SafetyClassifier

02ff4e4
verified

mlboydaisuke commited on Aug 14

Shieldstral-1.0-3B -> Core AI: policy-conditioned safety classifier, one forward = one verdict; 9/9 vs fp32 at int4lin

5ec6faf
verified

mlboydaisuke commited on Aug 14