model_611825449_beit_base.py

Model Overview

A base-scale implementation of the beit architecture, built for classification tasks.

Architecture

• Architecture: beit
• Scale: base
• Attention: multi query
• Fusion strategy: tensor fusion
• Task head: classification
• Activation: gelu tanh
• Normalization: layernorm
• Initialization: kaiming normal

Training

• Optimizer: lion
• LR scheduler: polynomial

Files

• model_611825449_beit_base.py — main artifact of this repository

License

See the license field above.