AI models
HGRN2 3B
Training compute
1.7×10²¹ FLOP
Parameters
2.9B
Published
Apr 11, 2024
HGRN2 3B is an AI model developed by Shanghai AI Lab, Massachusetts Institute of Technology (MIT) and Taptap (China, United States and Spain), first published in April 2024. It works in the language domain, on tasks such as language modeling/generation and question answering.
Training it took an estimated 1.7×10²¹ FLOP of compute (estimation method: operation counting). The model has 2,900,000,000 parameters. It was trained on roughly 100B datapoints.
Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- Shanghai AI Lab, Massachusetts Institute of Technology (MIT), Taptap
- Country of organization
- China, United States, Spain
- Domain
- Language
- Task
- Language modeling/generation, Question answering
- Training compute
- 1.7×10²¹ FLOP
- Compute estimation method
- Operation counting
- Parameters
- 2,900,000,000
- Dataset size
- 100B
- Epoch confidence
- Confident
More from Shanghai AI Lab,Massachusetts Institute of Technology (MIT),Taptap
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