model_540015763_hybrid_large.py
Model Overview
A large-scale implementation of the hybrid architecture, built for retrieval tasks.
Architecture
- Architecture: hybrid
- Scale: large
- Attention: sparse
- Fusion strategy: cross attention
- Task head: retrieval
- Activation: gelu
- Normalization: instancenorm
- Initialization: kaiming normal
Training
- Optimizer: lamb
- LR scheduler: cosine
Files
model_540015763_hybrid_large.py— main artifact of this repository
License
See the license field above.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support