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 →| Provider | Input (per 1M) | Output (per 1M) | Type | |
|---|---|---|---|---|
| Fireworks AI | $0.20 | $0.20 | Provisioned | |
| OctoAI API | $0.15 | $0.15 | Serverless | |
| Replicate API | $0.05 | $0.25 | Serverless |
Compare
All comparisons →Llama Guard 2 8B vs Qwen2 7B InstructLlama Guard 2 8B vs ShieldGemma 9BLlama Guard 2 8B vs Dracarys Llama 3.1 70B InstructLlama Guard 2 8B vs Gemma 2 9B SahabatAI InstructLlama Guard 2 8B vs Llama 3 Taiwan 70B InstructLlama Guard 2 8B vs Llama 3 Swallow 70B InstructLlama Guard 2 8B vs Llama 3.1 Swallow 8B InstructLlama Guard 2 8B vs Bielik 11B v2.6 InstructLlama Guard 2 8B vs Sarvam-M Multilingual HybridLlama Guard 2 8B vs Teuken 7B InstructLlama Guard 2 8B vs Italia 10B InstructLlama Guard 2 8B vs Colosseum 355B InstructLlama Guard 2 8B vs Stockmark 2 100B InstructLlama Guard 2 8B vs Seed-OSS 36B InstructLlama Guard 2 8B vs Marin 8B InstructLlama Guard 2 8B vs Granite Guardian 3.0 8B
Specifications
FamilyLlama Guard
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