LLM ReferenceLLM Reference

Llama Guard 2 8B

Open Source

About

Llama Guard 2 is an 8B-parameter LLM built on the Llama 3 architecture, specifically designed for content moderation tasks. Released by Meta on April 18, 2024, it excels in classifying both inputs and outputs of LLMs across 11 safety categories. The model generates text outputs indicating whether content is safe or unsafe, providing detailed feedback on violations. It aims to enhance user experience by minimizing false positives while maintaining high accuracy in content moderation, supporting developers in creating safer AI applications .

Capabilities

VisionMultimodalReasoningFunction CallingTool UseStructured OutputsCode Execution

Providers(3)

Compare all →
ProviderInput (per 1M)Output (per 1M)Type
Fireworks AI$0.20$0.20Provisioned
OctoAI API$0.15$0.15Serverless
Replicate API$0.05$0.25Serverless

Rankings

Specifications

Released2024-04-18
Parameters8B
Context8K
ArchitectureDecoder Only
Specializationgeneral
Trainingfinetuning

Created by

Large-scale open-source AI for social technologies.

Menlo Park, California, United States
Founded 2013
Website