model_113101117_flamingo_nano.py

Model Overview

A nano-scale implementation of the flamingo architecture, built for contrastive tasks.

Architecture

• Architecture: flamingo
• Scale: nano
• Attention: sparse
• Fusion strategy: tensor fusion
• Task head: contrastive
• Activation: relu
• Normalization: batchnorm
• Initialization: xavier uniform

Training

• Optimizer: novograd
• LR scheduler: exponential

Files

• model_113101117_flamingo_nano.py — main artifact of this repository

License

See the license field above.