model_180114885_blip_huge.py
Model Overview
A huge-scale implementation of the blip architecture, built for retrieval tasks.
Architecture
- Architecture: blip
- Scale: huge
- Attention: grouped query
- Fusion strategy: co attention
- Task head: retrieval
- Activation: swish
- Normalization: rmsnorm
- Initialization: xavier uniform
Training
- Optimizer: adam
- LR scheduler: onecycle
Files
model_180114885_blip_huge.py — main artifact of this repository
License
See the license field above.