← Back to search

Models tagged "llm-guardrails"

Sort by:

Found 2 models (showing 1-2)

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

lucataco/prompt-guard-86m

Detect prompt injection and jailbreak attempts in text inputs. Classify a string as benign, injection, and/or jailbreak...

text-classification • prompt-injection-detection • llm-safety • 31 runs