AI models
AbGPT
Training compute
4.3×10²¹ FLOP
Parameters
734M
Published
Sep 9, 2024
AbGPT is an AI model developed by Carnegie Mellon University (CMU) (United States), first published in September 2024. It works in the biology domain, on tasks such as protein design.
Training it took an estimated 4.3×10²¹ FLOP of compute. The model has 734,000,000 parameters. It was trained on roughly 6.8B datapoints. Training ran on NVIDIA RTX A6000.
Access: Unreleased. Its weights are not openly released. It is built on top of ProtGPT2. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- Carnegie Mellon University (CMU)
- Country of organization
- United States
- Domain
- Biology
- Task
- Protein design
- Training compute
- 4.3×10²¹ FLOP
- Parameters
- 734,000,000
- Dataset size
- 6.8B
- Training hardware
- NVIDIA RTX A6000
- Model accessibility
- Unreleased
- Open weights
- No
- Base model
- ProtGPT2
- Epoch confidence
- Confident
More from Carnegie Mellon University (CMU)
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