model_053464209_cnn_transformer_base.py

Model Overview

A base-scale implementation of the cnn transformer architecture, built for generation tasks.

Architecture

• Architecture: cnn transformer
• Scale: base
• Attention: sliding window
• Fusion strategy: cross attention
• Task head: generation
• Activation: approx gelu
• Normalization: instancenorm
• Initialization: kaiming normal

Training

• Optimizer: adamw
• LR scheduler: linear warmup

Files

• model_053464209_cnn_transformer_base.py — main artifact of this repository

License

See the license field above.