Chameleon-34B

Training compute

1.6×10²⁴ FLOP

Parameters

34B

Published

May 16, 2024

Chameleon-34B is an AI model developed by Facebook AI Research (United States and France), first published in May 2024. It works in the multimodal, image generation, language and vision domain, on tasks such as language modeling/generation, vision-language generation, visual question answering and text-to-image.

Training it took an estimated 1.6×10²⁴ FLOP of compute (estimation method: hardware,operation counting). The model has 34,000,000,000 parameters. It was trained on roughly 4.4T datapoints. Training ran on 3,072 NVIDIA A100 SXM4 80 GB for about 1.4K hours.

Access: Open weights (non-commercial). Its weights are openly available. Epoch AI rates the confidence of this record as confident.

Full record

Organization: Facebook AI Research
Country of organization: United States, France
Domain: Multimodal, Image generation, Language, Vision
Task: Language modeling/generation, Vision-language generation, Visual question answering, Text-to-image
Training compute: 1.6×10²⁴ FLOP
Compute estimation method: Hardware, Operation counting
Parameters: 34,000,000,000
Dataset size: 4.4T
Training hardware: NVIDIA A100 SXM4 80 GB
Chips used: 3,072
Training time: 1,394 h
Training power draw: 2.4 MW
Model accessibility: Open weights (non-commercial)
Open weights: Yes
Epoch confidence: Confident