model_417131709_poolformer_tiny.py

Model Overview

A tiny-scale implementation of the poolformer architecture, built for generation tasks.

Architecture

• Architecture: poolformer
• Scale: tiny
• Attention: grouped query
• Fusion strategy: gated fusion
• Task head: generation
• Activation: gelu
• Normalization: batchnorm
• Initialization: orthogonal

Training

• Optimizer: adafactor
• LR scheduler: linear warmup

Files

• model_417131709_poolformer_tiny.py — main artifact of this repository

License

See the license field above.