model_497488431_mixer_base.py
Model Overview
A base-scale implementation of the mixer architecture, built for retrieval tasks.
Architecture
- Architecture: mixer
- Scale: base
- Attention: standard
- Fusion strategy: tensor fusion
- Task head: retrieval
- Activation: swish
- Normalization: rmsnorm
- Initialization: trunc normal
Training
- Optimizer: rmsprop
- LR scheduler: onecycle
Files
model_497488431_mixer_base.py — main artifact of this repository
License
See the license field above.
