model_173026814_blip_xlarge.py

Model Overview

A xlarge-scale implementation of the blip architecture, built for classification tasks.

Architecture

• Architecture: blip
• Scale: xlarge
• Attention: sparse
• Fusion strategy: cross attention
• Task head: classification
• Activation: swish
• Normalization: instancenorm
• Initialization: xavier uniform

Training

• Optimizer: adafactor
• LR scheduler: step

Files

• model_173026814_blip_xlarge.py — main artifact of this repository

License

See the license field above.