Fnet Base
Google's FNet Base model is a transformer-based AI model that replaces traditional attention mechanisms with Fourier transforms, allowing it to process input sequences without attention masks. It is particularly effective at learning bidirectional representations of sentences through its pretraining objectives, including masked language modeling and next sentence prediction.
Input
Output
Context
1K
Max Output
-
Parameters
83M
Technical Specifications
Model TypeEmbedding
Context Window512 tokens
Max Output TokensNot available
Parameters83M
Release DateMar 2, 2022
Training CutoffNot available
Licenseapache-2.0
Open SourceYes
Input Modalities
Text
Output Modalities
Embedding
Capabilities
Estimated GPU Requirements for Fnet Base
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jun 23, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.