AI models
BITTERS
Training compute
7.8×10¹⁷ FLOP
Parameters
650M
Published
Oct 1, 2023
BITTERS is an AI model developed by LG and Shutterstock (South Korea and United States), first published in October 2023. It works in the vision domain, on tasks such as image captioning.
Training it took an estimated 7.8×10¹⁷ FLOP of compute (estimation method: operation counting). The model has 650,000,000 parameters. It was trained on roughly 108.8B datapoints.
Access: Unreleased. Its weights are not openly released. Epoch AI rates the confidence of this record as likely.
Full record
- Organization
- LG, Shutterstock
- Country of organization
- South Korea, United States
- Domain
- Vision
- Task
- Image captioning
- Training compute
- 7.8×10¹⁷ FLOP
- Compute estimation method
- Operation counting
- Parameters
- 650,000,000
- Dataset size
- 108.8B
- Model accessibility
- Unreleased
- Open weights
- No
- Epoch confidence
- Likely
SourceEpoch AI, 'AI Models'. Published online at epoch.ai. Retrieved 2026-07-29 from https://epoch.ai/data/ai-models. Licensed under CC BY 4.0.
← All ai models