Project AURIONAI Use-Cases Research & Innovation
Allen AI
guard

WildGuard 7B

Allen AI's guard model for prompt harm, response harm and refusal detection; paper reports beating Llama-Guard2 and Aegis-Guard, up to +25.3% F1 on refusal detection.

Allen AIAllen AIUSA
Figure from the WildGuard paper: WildGuardMix data and the three moderation tasks.
Levelmodel
Classguard
Parameters7B
Contextnot in the notes
ReleasedJun 2024
Opennessopen weights permissive
Runs onnot in the notes
Statusactive

Lineage

finetune
Mistral-7B-v0.3 to WildGuard 7B: finetune, high confidenceMistral-7B-v0.3Mistral-7B-v0.3Mistral AIWildGuard 7BWildGuard 7BAllen AI, Jun 2024
Mistral AIMistral-7B-v0.3 is the parent (finetune)high confidencemodel card
Where this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. The tree shows two generations each way, 2 models. Confidence and evidence are the notes' own.

R&D Topics

Guardrails and safety classifiersproduced by

Identity

Developer
Allen AI
Family
not in the notes
Released
Jun 2024 sourcesnotes
Weights published
–
Record checked
10 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.

Architecture and Size

Architecture
not in the notes
Total parameters
7B sources
Active parameters
–
Checkpoint parameters
–
Context length
not in the notes
Input
text
Output
text
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).

Openness and Access

Openness
open weights permissive
Licence
Apache License 2.0 sources
Access routes
open weights download
Where this comes from
The licence file governs over registry tags and aggregator labels.

Deployment

Runs on
not in the notes
Footprint
not in the notes
Runtimes
not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.

Indonesia

Indonesian support
not stated
Regional languages
not in the notes
Jakarta hosting
unknown
Languages
English
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.

Benchmark Results

The notes record no benchmark result for this model.

Industry Use Cases

No industry use case links this model.

Sources

  1. allenai/wildguard , Hugging Face huggingface.co https://huggingface.co/allenai/wildguard

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "WildGuard 7B", https://aurion.semai.id/models/allen-ai-wildguard-7b/, records of October 2026.