AI models
ChemBERTa
Training compute
8.5×10¹⁸ FLOP
Parameters
125M
Published
Oct 23, 2020
ChemBERTa is an AI model developed by University of Toronto, Reverie Labs and DeepChem (Canada and United States), first published in October 2020. It works in the biology domain, on tasks such as molecular property prediction.
Training it took an estimated 8.5×10¹⁸ FLOP of compute (estimation method: operation counting,hardware). The model has 125,000,000 parameters. It was trained on roughly 225M datapoints. Training ran on 1 NVIDIA V100 for about 48 hours.
Access: Open weights (unrestricted). Its weights are openly available. Epoch AI rates the confidence of this record as likely.
Full record
- Organization
- University of Toronto, Reverie Labs, DeepChem
- Country of organization
- Canada, United States
- Domain
- Biology
- Task
- Molecular property prediction
- Training compute
- 8.5×10¹⁸ FLOP
- Compute estimation method
- Operation counting, Hardware
- Parameters
- 125,000,000
- Dataset size
- 225M
- Training hardware
- NVIDIA V100
- Chips used
- 1
- Training time
- 48 h
- Training power draw
- 335 W
- Model accessibility
- Open weights (unrestricted)
- Open weights
- Yes
- 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