AI models
LMRec
Training compute
2×10¹⁸ FLOP
Parameters
210M
Published
May 13, 2023
LMRec is an AI model developed by NAVER and Naver AI Lab (South Korea), first published in May 2023. It works in the language and recommendation domain, on tasks such as language modeling/generation.
Training it took an estimated 2×10¹⁸ FLOP of compute (estimation method: operation counting). The model has 210,000,000 parameters. It was trained on roughly 13B datapoints.
Epoch AI rates the confidence of this record as likely.
Full record
- Organization
- NAVER, Naver AI Lab
- Country of organization
- South Korea
- Domain
- Language, Recommendation
- Task
- Language modeling/generation
- Training compute
- 2×10¹⁸ FLOP
- Compute estimation method
- Operation counting
- Parameters
- 210,000,000
- Dataset size
- 13B
- 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