AI models
LIMA
Training compute
5.5×10²³ FLOP
Parameters
65B
Published
May 18, 2023
LIMA is an AI model developed by Meta AI, Carnegie Mellon University (CMU), University of Southern California and Tel Aviv University (United States and Israel), first published in May 2023. It works in the language domain, on tasks such as chat and language modeling/generation.
Training it took an estimated 5.5×10²³ FLOP of compute (estimation method: operation counting). The model has 65,000,000,000 parameters. It was trained on roughly 685.3K datapoints.
Access: Unreleased. Its weights are not openly released. It is built on top of LLaMA-65B. The reference paper has 1,274 citations. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- Meta AI, Carnegie Mellon University (CMU), University of Southern California, Tel Aviv University
- Country of organization
- United States, Israel
- Domain
- Language
- Task
- Chat, Language modeling/generation
- Training compute
- 5.5×10²³ FLOP
- Compute estimation method
- Operation counting
- Parameters
- 65,000,000,000
- Dataset size
- 685.3K
- Model accessibility
- Unreleased
- Open weights
- No
- Base model
- LLaMA-65B
- Citations
- 1,274
- 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