safety-classification AI Models

🤖 Model

meta/llama-guard-4-12b

Moderate text prompts, model responses, and images for safety compliance. Accepts text with optional multiple images and...

content-moderation • safety-classification • multimodal • 46.3K runs

🤖 Model 📝 → 📝

meta/meta-llama-guard-2-8b

Classifies content in LLM prompts and responses for safety and harm detection. Built on Llama 3 with 8 billion parameter...

📝 → 📝 • text-generation • content-moderation • safety-detection • 790.0K runs

🤖 Model

meta/llamaguard-7b

Moderate text prompts and assistant responses for safety and policy compliance. Accepts a user message (prompt) and/or a...

content-moderation • safety-classification • text-classification • 26 runs

🤖 Model 📝 → 📝

meta/llama-guard-3-8b

Classify text content for safety and content moderation based on the MLCommons hazards taxonomy. Built on Llama-3.1-8B a...

📝 → 📝 • text-generation • content-moderation • safety-classification • 382.7K runs

🤖 Model 🖼️

meta/llama-guard-3-11b-vision

Classify the safety of multimodal inputs (image and user message) for content moderation. Accepts an image (required) an...

🖼️ • content-moderation • multimodal-safety • image-nsfw-detection • 1.5K runs

🤖 Model 📝 → 📝

lucataco/gpt-oss-safeguard-120b

Classifies text content based on custom safety policies written in plain English. Trained specifically for safety reason...

📝 → 📝 • text-generation • content-moderation • safety-classification • 52 runs

🤖 Model 📝 → 📝

ditto--ai/qwen3guard-gen-4b

Classifies text content for safety and moderation, analyzing user prompts and assistant responses to determine if they a...

📝 → 📝 • text-generation • content-moderation • 733.1K runs

🤖 Model 📝 → 📝

lucataco/gpt-oss-safeguard-20b

Classify text content based on custom safety policies you provide. Takes a text prompt and your written safety policy as...

📝 → 📝 • text-generation • content-moderation • safety-classification • 46 runs