Llama Guard

Training compute

1.6×10²³ FLOP

Parameters

7B

Published

Dec 7, 2023

Llama Guard is an AI model developed by Meta AI (United States), first published in December 2023. It works in the language domain, on tasks such as chat.

Training it took an estimated 1.6×10²³ FLOP of compute (estimation method: operation counting). The model has 7,000,000,000 parameters. It was trained on roughly 4.1M datapoints. Training ran on NVIDIA A100 SXM4 80 GB.

Access: Open weights (restricted use). Its weights are openly available. It is built on top of Llama 2-7B. The reference paper has 987 citations. Epoch AI rates the confidence of this record as confident.

Full record

Organization: Meta AI
Country of organization: United States
Domain: Language
Task: Chat
Training compute: 1.6×10²³ FLOP
Compute estimation method: Operation counting
Parameters: 7,000,000,000
Dataset size: 4.1M
Training hardware: NVIDIA A100 SXM4 80 GB
Model accessibility: Open weights (restricted use)
Open weights: Yes
Base model: Llama 2-7B
Citations: 987
Epoch confidence: Confident