AI models
BiRNA-BERT
Training compute
1.8×10¹⁹ FLOP
Parameters
117M
Published
Nov 18, 2024
BiRNA-BERT is an AI model developed by Bangladesh University of Engineering and Technology, University of California Riverside and Carnegie Mellon University (CMU) (India and United States), first published in November 2024. It works in the biology domain, on tasks such as protein or nucleotide language model (plm/nlm) and entity embedding.
Training it took an estimated 1.8×10¹⁹ FLOP of compute (estimation method: hardware,operation counting). The model has 117,000,000 parameters. It was trained on roughly 32.3B datapoints. Training ran on 8 NVIDIA GeForce RTX 3090 for about 48.42 hours.
Access: Open weights (non-commercial). Its weights are openly available. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- Bangladesh University of Engineering and Technology, University of California Riverside, Carnegie Mellon University (CMU)
- Country of organization
- India, United States
- Domain
- Biology
- Task
- Protein or nucleotide language model (pLM/nLM), Entity embedding
- Training compute
- 1.8×10¹⁹ FLOP
- Compute estimation method
- Hardware, Operation counting
- Parameters
- 117,000,000
- Dataset size
- 32.3B
- Training hardware
- NVIDIA GeForce RTX 3090
- Chips used
- 8
- Training time
- 48 h
- Training power draw
- 5.5 kW
- Model accessibility
- Open weights (non-commercial)
- Open weights
- Yes
- 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