ProtT5-XXL-BFD
ProtT5-XXL-BFD is an AI model developed by Technical University of Munich, Med AI Technology, NVIDIA, Oak Ridge National Laboratory, Google and Seoul National University (Germany, China, United States and South Korea), first published in May 2021. It works in the biology domain, on tasks such as proteins, protein or nucleotide language model (plm/nlm) and protein representation learning.
Training it took an estimated 3.7×10²² FLOP of compute (estimation method: operation counting). The model has 11,000,000,000 parameters. It was trained on roughly 393B datapoints. Training ran on 512 Google TPU v3. The compute alone is estimated at $43K in 2023 dollars.
Access: Open weights (unrestricted). Its weights are openly available. Epoch AI rates the confidence of this record as confident.
- Organization
- Technical University of Munich, Med AI Technology, NVIDIA, Oak Ridge National Laboratory, Google, Seoul National University
- Country of organization
- Germany, China, United States, South Korea
- Domain
- Biology
- Task
- Proteins, Protein or nucleotide language model (pLM/nLM), Protein representation learning
- Training compute
- 3.7×10²² FLOP
- Compute estimation method
- Operation counting
- Parameters
- 11,000,000,000
- Dataset size
- 393B
- Training hardware
- Google TPU v3
- Chips used
- 512
- Training power draw
- 466.5 kW
- Training cost (2023 USD)
- $43K
- Numerical format
- FP32
- Model accessibility
- Open weights (unrestricted)
- Open weights
- Yes
- Epoch confidence
- Confident