AI models
BIDAF
Training compute
3.5×10¹⁸ FLOP
Parameters
2.6M
Published
Nov 5, 2016
BIDAF is an AI model developed by University of Washington and Allen Institute for AI (United States), first published in November 2016. It works in the language domain, on tasks such as question answering.
Training it took an estimated 3.5×10¹⁸ FLOP of compute (estimation method: hardware). The model has 2,600,000 parameters. It was trained on roughly 879K datapoints. Training ran on 8 NVIDIA GeForce GTX TITAN X for about 60 hours. The compute alone is estimated at $41 in 2023 dollars.
Access: Open weights (unrestricted). Its weights are openly available. The reference paper has 2,246 citations. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- University of Washington, Allen Institute for AI
- Country of organization
- United States
- Domain
- Language
- Task
- Question answering
- Training compute
- 3.5×10¹⁸ FLOP
- Compute estimation method
- Hardware
- Parameters
- 2,600,000
- Dataset size
- 879K
- Training hardware
- NVIDIA GeForce GTX TITAN X
- Chips used
- 8
- Training time
- 60 h
- Chip-hours
- 480
- Training power draw
- 4.2 kW
- Training cost (2023 USD)
- $41
- Model accessibility
- Open weights (unrestricted)
- Open weights
- Yes
- Citations
- 2,246
- Epoch confidence
- Confident
More from University of Washington,Allen Institute for AI
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