Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
mlboydaisuke
/
Shieldstral-CoreAI
like
1
Text Classification
mistral3
coreai
aimodel
apple-silicon
on-device
safety
moderation
classifier
mistral
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
Shieldstral-CoreAI
10.1 GB
Ctrl+K
Ctrl+K
1 contributor
History:
7 commits
mlboydaisuke
Shieldstral-1.0-3B -> Core AI: policy-conditioned safety classifier, one forward = one verdict; 9/9 vs fp32 at int4lin
777ac29
verified
about 15 hours ago
gpu-classify
reference.json: ship the nine gated cases with their fp32 probabilities
2 days ago
ios-h18p
Shieldstral-1.0-3B -> Core AI: policy-conditioned safety classifier, one forward = one verdict; 9/9 vs fp32 at int4lin
about 15 hours ago
.gitattributes
2.73 kB
Shieldstral-1.0-3B -> Core AI: policy-conditioned safety classifier, one forward = one verdict; 9/9 vs fp32 at int4lin
about 15 hours ago
README.md
6.7 kB
Shieldstral-1.0-3B -> Core AI: policy-conditioned safety classifier, one forward = one verdict; 9/9 vs fp32 at int4lin
about 15 hours ago
config.json
Safe
1.65 kB
Shieldstral-1.0-3B -> Core AI: policy-conditioned safety classifier, one forward = one verdict; 9/9 vs fp32 at int4lin
2 days ago
