AI models
EPInformer
Training compute
3.4×10¹⁷ FLOP
Parameters
447.1K
Published
Aug 1, 2024
EPInformer is an AI model developed by The University of Hong Kong and Harvard Medical School (Hong Kong and United States), first published in August 2024. It works in the biology domain, on tasks such as gene expression profile generation.
Training it took an estimated 3.4×10¹⁷ FLOP of compute. The model has 447,149 parameters. Training ran on 1 NVIDIA A100 for about 1 hours.
The reference paper has 2 citations. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- The University of Hong Kong, Harvard Medical School
- Country of organization
- Hong Kong, United States
- Domain
- Biology
- Task
- Gene expression profile generation
- Training compute
- 3.4×10¹⁷ FLOP
- Parameters
- 447,149
- Training hardware
- NVIDIA A100
- Chips used
- 1
- Training time
- 1 h
- Training power draw
- 433 W
- Citations
- 2
- Epoch confidence
- Confident
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