Llama SEA-LION V2 8B

Training compute

7.2×10²³ FLOP

Parameters

8B

Published

Jul 30, 2024

Llama SEA-LION V2 8B is an AI model developed by AI Singapore (Singapore), first published in July 2024. It works in the language domain, on tasks such as question answering, chat and language modeling/generation.

Training it took an estimated 7.2×10²³ FLOP of compute (estimation method: hardware,operation counting). The model has 8,000,000,000 parameters. It was trained on roughly 48B datapoints. Training ran on 64 NVIDIA H100 SXM5 80GB for about 48 hours.

Access: Open weights (restricted use). Its weights are openly available. It is built on top of Llama 3-8B. Epoch AI rates the confidence of this record as confident.

Full record

Organization: AI Singapore
Country of organization: Singapore
Domain: Language
Task: Question answering, Chat, Language modeling/generation
Training compute: 7.2×10²³ FLOP
Compute estimation method: Hardware, Operation counting
Parameters: 8,000,000,000
Dataset size: 48B
Training hardware: NVIDIA H100 SXM5 80GB
Chips used: 64
Training time: 48 h
Training power draw: 88.4 kW
Numerical format: BF16
Model accessibility: Open weights (restricted use)
Open weights: Yes
Base model: Llama 3-8B
Epoch confidence: Confident