AI models
PMLM-large
Training compute
3.8×10²¹ FLOP
Parameters
250M
Published
Oct 21, 2021
PMLM-large is an AI model developed by Microsoft Research Asia, Nanyang Technological University, Xi’an Jiaotong University and Sun Yat-sen University (China and Singapore), first published in October 2021. It works in the biology domain, on tasks such as protein or nucleotide language model (plm/nlm).
Training it took an estimated 3.8×10²¹ FLOP of compute (estimation method: hardware). The model has 250,000,000 parameters. Training ran on 24 NVIDIA V100 for about 1.2K hours.
The reference paper has 36 citations. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- Microsoft Research Asia, Nanyang Technological University, Xi’an Jiaotong University, Sun Yat-sen University
- Country of organization
- China, Singapore
- Domain
- Biology
- Task
- Protein or nucleotide language model (pLM/nLM)
- Training compute
- 3.8×10²¹ FLOP
- Compute estimation method
- Hardware
- Parameters
- 250,000,000
- Training hardware
- NVIDIA V100
- Chips used
- 24
- Training time
- 1,176 h
- Training power draw
- 14.5 kW
- Citations
- 36
- 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