Llama Guard 3
Llama Guard 3 is Meta’s open-weight safety model for moderating AI prompts and responses. It classifies policy risks, returns structured JSON (allow/block with categories and rationale), and is designed to run beside your assistant for low-latency, context-aware guardrails.
- Type
- Text
- Weights
- Open
- Downloads
- 59k
- Likes
- 322
- Pipeline
- text generation
- License
- llama3.1
Model hub
meta-llama/Llama-Guard-3-8B
- Repo
- meta-llama/Llama-Guard-3-8B
- Library
- transformers
- Access
- Gated
Technical tags and languages
Papers
4
Related tools
1
More from Meta Platforms
13
-
Brain2Qwerty v2
Multimodal
End-to-end deep learning pipeline that decodes text in real time from non-invasive magnetoencephalography (ME…
-
Canopy Height Maps v2
Image
Canopy Height Maps v2 (CHMv2) is a global, meter-resolution tree canopy height mapping system built from high…
-
CM3leon
Image
AI model by Meta Platforms
-
Code Llama
Text
AI model by Meta Platforms
-
DexWM (Dexterous Interaction World Model)
Multimodal
DexWM is a dexterous interaction world model for learning hand-object interactions from human videos. It pred…
-
DINOv2
Image
DINOv2 is a self-supervised Vision Transformer developed by Meta AI that learns general-purpose visual featur…
-
DINOv3
Image
DINOv3 is a self supervised computer vision model from Meta that produces universal image backbones without u…
-
Emu Video
Video
AI model by Meta Platforms
About Meta Platforms
1
We're connecting people to what they care about, powering new, meaningful experiences, and advancing the state-of-the-art through open research and accessible tooling.
Tools using Llama Guard 3
8