model_143025998_flamingo_huge.py
Model Overview
A huge-scale implementation of the flamingo architecture, built for retrieval tasks.
Architecture
- Architecture: flamingo
- Scale: huge
- Attention: grouped query
- Fusion strategy: concat mlp
- Task head: retrieval
- Activation: relu
- Normalization: groupnorm
- Initialization: kaiming
Training
- Optimizer: lamb
- LR scheduler: exponential
Files
model_143025998_flamingo_huge.py — main artifact of this repository
License
See the license field above.
