model_042624597_cnn_transformer_tiny.py

Model Overview

A tiny-scale implementation of the cnn transformer architecture, built for matching tasks.

Architecture

• Architecture: cnn transformer
• Scale: tiny
• Attention: linear
• Fusion strategy: gated fusion
• Task head: matching
• Activation: approx gelu
• Normalization: scalenorm
• Initialization: trunc normal

Training

• Optimizer: adafactor
• LR scheduler: linear warmup

Files

• model_042624597_cnn_transformer_tiny.py — main artifact of this repository

License

See the license field above.