AI models
ALiBi (L=3072, Lvalid = 3072)
Training compute
8.1×10²⁰ FLOP
Parameters
1.3B
Published
Aug 27, 2021
ALiBi (L=3072, Lvalid = 3072) is an AI model developed by University of Washington, Facebook AI Research and Allen Institute for AI (United States and France), first published in August 2021. It works in the language domain, on tasks such as language modeling.
Training it took an estimated 8.1×10²⁰ FLOP of compute (estimation method: hardware). The model has 1,300,000,000 parameters.
Access: Open weights (unrestricted). Its weights are openly available. The reference paper has 1,194 citations. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- University of Washington, Facebook AI Research, Allen Institute for AI
- Country of organization
- United States, France
- Domain
- Language
- Task
- Language modeling
- Training compute
- 8.1×10²⁰ FLOP
- Compute estimation method
- Hardware
- Parameters
- 1,300,000,000
- Model accessibility
- Open weights (unrestricted)
- Open weights
- Yes
- Citations
- 1,194
- Epoch confidence
- Confident
More from University of Washington,Facebook AI Research,Allen Institute for AI
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