← Back to search

Models tagged "prompt-moderation"

Sort by:

Found 2 models (showing 1-2)

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

Moderate LLM prompts and responses for safety policy compliance. Accepts a user prompt and/or an assistant reply as text...

content-moderation • safety-classification • text-classification • 734.9K runs

fofr/prompt-classifier

Classify text prompts for text-to-image systems and return a safety score from 0 (safe) to 10 (very NSFW/toxic). Accepts...

text-safety • text-nsfw-detection • toxicity-detection • 1.9M runs