model_099723153_perceiver_xlarge.py
Model Overview
A xlarge-scale implementation of the perceiver architecture, built for classification tasks.
Architecture
- Architecture: perceiver
- Scale: xlarge
- Attention: flash
- Fusion strategy: tensor fusion
- Task head: classification
- Activation: relu
- Normalization: layernorm
- Initialization: kaiming normal
Training
- Optimizer: adafactor
- LR scheduler: constant warmup
Files
model_099723153_perceiver_xlarge.py— main artifact of this repository
License
See the license field above.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support