AI models
Hybrid-Phi-Mamba-1.5B
Training compute
1.2×10²¹ FLOP
Parameters
1.5B
Published
Aug 19, 2024
Hybrid-Phi-Mamba-1.5B is an AI model developed by Carnegie Mellon University (CMU), Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) and Cartesia (United States and United Arab Emirates), first published in August 2024. It works in the language domain, on tasks such as language modeling/generation.
Training it took an estimated 1.2×10²¹ FLOP of compute (estimation method: operation counting). The model has 1,500,000,000 parameters. It was trained on roughly 5B datapoints.
Access: Unreleased. Its weights are not openly released. It is built on top of Phi-1.5. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- Carnegie Mellon University (CMU), Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), Cartesia
- Country of organization
- United States, United Arab Emirates
- Domain
- Language
- Task
- Language modeling/generation
- Training compute
- 1.2×10²¹ FLOP
- Compute estimation method
- Operation counting
- Parameters
- 1,500,000,000
- Dataset size
- 5B
- Model accessibility
- Unreleased
- Open weights
- No
- Base model
- Phi-1.5
- 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