model_147584158_flamingo_giant.py
Model Overview
A giant-scale implementation of the flamingo architecture, built for generation tasks.
Architecture
- Architecture: flamingo
- Scale: giant
- Attention: grouped query
- Fusion strategy: co attention
- Task head: generation
- Activation: gelu
- Normalization: groupnorm
- Initialization: kaiming
Training
- Optimizer: lion
- LR scheduler: linear warmup
Files
model_147584158_flamingo_giant.py — main artifact of this repository
License
See the license field above.