Llama 2-70B

Training compute

8.1×10²³ FLOP

Parameters

70B

Published

Jul 18, 2023

Llama 2-70B is an AI model developed by Meta AI (United States), first published in July 2023. It works in the language domain, on tasks such as language modeling, language modeling/generation and question answering.

Training it took an estimated 8.1×10²³ FLOP of compute (estimation method: hardware,operation counting). The model has 70,000,000,000 parameters. It was trained on roughly 2T datapoints. Training ran on 1,000 NVIDIA A100 SXM4 80 GB for about 1.7K hours. The compute alone is estimated at $1M in 2023 dollars.

Access: Open weights (restricted use). Its weights are openly available. The reference paper has 16,911 citations. Epoch AI rates the confidence of this record as confident.

Full record

Organization: Meta AI
Country of organization: United States
Domain: Language
Task: Language modeling, Language modeling/generation, Question answering
Training compute: 8.1×10²³ FLOP
Compute estimation method: Hardware, Operation counting
Parameters: 70,000,000,000
Dataset size: 2T
Training hardware: NVIDIA A100 SXM4 80 GB
Chips used: 1,000
Training time: 1,728 h
Chip-hours: 1.7M
Training power draw: 795.6 kW
Training cost (2023 USD): $1M
Model accessibility: Open weights (restricted use)
Open weights: Yes
Citations: 16,911
Epoch confidence: Confident

Benchmark results

01

Epoch Capabilities Index

ECI Score

113.7