AI models
ProLLaMA
Training compute
8.4×10²² FLOP
Parameters
7B
Published
Feb 26, 2024
ProLLaMA is an AI model developed by Peking University and Peng Cheng Laboratory (China), first published in February 2024. It works in the biology domain, on tasks such as protein question answering.
Training it took an estimated 8.4×10²² FLOP of compute (estimation method: hardware). The model has 7,000,000,000 parameters. Training ran on 8 NVIDIA RTX A6000 for about 264 hours.
It is built on top of Llama 2-7B. The reference paper has 84 citations. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- Peking University, Peng Cheng Laboratory
- Country of organization
- China
- Domain
- Biology
- Task
- Protein question answering
- Training compute
- 8.4×10²² FLOP
- Compute estimation method
- Hardware
- Parameters
- 7,000,000,000
- Training hardware
- NVIDIA RTX A6000
- Chips used
- 8
- Training time
- 264 h
- Training power draw
- 4.7 kW
- Base model
- Llama 2-7B
- Citations
- 84
- 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