Guardrails - a ttttonyhe Collection

ttttonyhe 's Collections

Red-Teaming Datasets

Guardrail Datasets and Benchmarks

Prompt Injection Defenses

Specialized LLMs

Red-Teaming Models

Safety Alignment Datasets

Embedding Models

Domain-specific Datasets

Novel Model Architectures

Guardrails

updated Jun 14

openai/gpt-oss-safeguard-20b

Text Generation • 22B • Updated Jan 14 • 112k • • 250
Qwen/Qwen3Guard-Stream-0.6B

Feature Extraction • 0.6B • Updated Nov 7, 2025 • 2.46k • 33
meta-llama/Llama-Guard-4-12B

Image-Text-to-Text • 12B • Updated Apr 29, 2025 • 192k • • 119
meta-llama/Llama-Prompt-Guard-2-86M

Text Classification • 0.3B • Updated Apr 29, 2025 • 128k • • 177
protectai/deberta-v3-base-prompt-injection-v2

Text Classification • 0.2B • Updated Jul 9 • 409k • • 112
leolee99/PIGuard

Text Classification • 0.2B • Updated Aug 3, 2025 • 32.5k • 10
allenai/wildguard

Text Generation • 7B • Updated Jul 27, 2025 • 127k • 56
nvidia/Llama-3.1-Nemotron-Safety-Guard-8B-v3

Text Generation • 8B • Updated Oct 28, 2025 • 2.9k • • 22
deepset/deberta-v3-base-injection

Text Classification • 0.2B • Updated Oct 15, 2024 • 13.3k • • 44
ibm-granite/granite-guardian-3.3-8b

Text Generation • 8B • Updated Sep 9, 2025 • 10.4k • 33
superagent-ai/superagent-guard-4b

Text Generation • 4B • Updated Jan 2 • 18