Meta · Moderation
Llama Guard 3 8B
Llama Guard 3 is a Llama-3.1-8B pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM inputs (prompt classification) and in LLM responses (response classification). It acts as an LLM – it generates text in its output that indicates whether a given prompt or response is safe or unsafe, and if unsafe, it also lists the content categories violated.
Evidence and sources
🤗 meta-llama/Llama-Guard-3-8B
Model architecture, as its sources state it
Fair value (49.6). Costs per task about what its benchmark results predict. From 1 benchmark with measured task costs. Little data behind it, so treat it as a rough estimate.How Value for money worksReleased 22 Jul 2024Maker HQ: US (according to Meta's own website)
Sources: Cloudflare Workers AI, Models.dev data, Hugging FacePrimary data from Cloudflare Workers AI
from Models.dev: name, weights availability
from Hugging Face: release date
Input & output
as stated by the model's providersText
Text
Also known as: @cf/meta/llama-guard-3-8b, cloudflare/@cf/meta/llama-guard-3-8b, deepinfra/meta-llama/llama-guard-3-8b, fireworks_ai/accounts/fireworks/models/llama-guard-3-8b, meta-llama/llama-guard-3-8b, meta/llama-guard-3-8b, nebius/meta-llama/llama-guard-3-8b
Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works