model_163483436_blip_base.py

Model Overview

A base-scale implementation of the blip architecture, built for generation tasks.

Architecture

• Architecture: blip
• Scale: base
• Attention: linear
• Fusion strategy: tucker
• Task head: generation
• Activation: swish
• Normalization: scalenorm
• Initialization: kaiming normal

Training

• Optimizer: adamw
• LR scheduler: polynomial

Files

• model_163483436_blip_base.py — main artifact of this repository

License

See the license field above.