AI models
CPM-Ant
Training compute
2×10²² FLOP
Parameters
10B
Published
Sep 22, 2022
CPM-Ant is an AI model developed by Tsinghua University, Beijing Academy of Artificial Intelligence / BAAI, ModelBest and OpenBMB (Open Lab for Big Model Base) (China), first published in September 2022. It works in the language domain, on tasks such as language modeling/generation and question answering.
Training it took an estimated 2×10²² FLOP of compute (estimation method: operation counting). The model has 10,000,000,000 parameters. It was trained on roughly 33.4B datapoints. The compute alone is estimated at $67K in 2023 dollars.
Access: Open weights (non-commercial). Its weights are openly available. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- Tsinghua University, Beijing Academy of Artificial Intelligence / BAAI, ModelBest, OpenBMB (Open Lab for Big Model Base)
- Country of organization
- China
- Domain
- Language
- Task
- Language modeling/generation, Question answering
- Training compute
- 2×10²² FLOP
- Compute estimation method
- Operation counting
- Parameters
- 10,000,000,000
- Dataset size
- 33.4B
- Training time
- 1,632 h
- Training cost (2023 USD)
- $67K
- Model accessibility
- Open weights (non-commercial)
- Open weights
- Yes
- Epoch confidence
- Confident
More from Tsinghua University,Beijing Academy of Artificial Intelligence / BAAI,ModelBest,OpenBMB (Open Lab for Big Model Base)
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