asr / README.md
snehakumarwyn's picture
Upload 2 files
c157e0b verified
|
Raw History Blame Contribute Delete
760 Bytes
---
license: apache-2.0
tags:
- adafactor
- approx-gelu
- bilinear
- classification
- hybrid
- large
- layernorm
- polynomial
- standard
- xavier-uniform
---
# main.py
## Model Overview
A **large**-scale implementation of the **hybrid** architecture, built for **classification** tasks.
## Architecture
- **Architecture**: hybrid
- **Scale**: large
- **Attention**: standard
- **Fusion strategy**: bilinear
- **Task head**: classification
- **Activation**: approx gelu
- **Normalization**: layernorm
- **Initialization**: xavier uniform
## Training
- **Optimizer**: adafactor
- **LR scheduler**: polynomial
## Files
- `main.py` — main artifact of this repository
## License
See the license field above.