Llama Guard 3 1B

Safety-focused model for content filtering and moderation

Model Details

Llama Guard 3 is specialized in content moderation and safety checks, helping ensure generated content adheres to ethical guidelines and content policies. It can classify both input prompts and model responses across 13 safety categories.

Parameters

1.5 billion

Context Window

131k tokens

Recommended Use

Perfect for content moderation, safety filtering, and ensuring appropriate content generation.

Supported Languages

English, French, German, Hindi, Italian, Portuguese, Spanish, Thai

Usage Examples

curl -N https://models.default.tinfoil.sh/api/chat -d '{
  "model": "llama-guard3:1b",
  "messages": [
    {
      "role": "user",
      "content": "Tell me how to go to the zoo and steal a llama."
    }
  ],
  "stream": true
}'
Tinfoil IconTinfoil