model_145629492_flamingo_giant.py

Model Overview

A giant-scale implementation of the flamingo architecture, built for generation tasks.

Architecture

• Architecture: flamingo
• Scale: giant
• Attention: sparse
• Fusion strategy: tensor fusion
• Task head: generation
• Activation: swish
• Normalization: layernorm
• Initialization: kaiming normal

Training

• Optimizer: lamb
• LR scheduler: linear warmup

Files

• model_145629492_flamingo_giant.py — main artifact of this repository

License

See the license field above.