model_161753475_blip_small.py

Model Overview

A small-scale implementation of the blip architecture, built for retrieval tasks.

Architecture

• Architecture: blip
• Scale: small
• Attention: grouped query
• Fusion strategy: tucker
• Task head: retrieval
• Activation: swish
• Normalization: layernorm
• Initialization: kaiming normal

Training

• Optimizer: rmsprop
• LR scheduler: step

Files

• model_161753475_blip_small.py — main artifact of this repository

License

See the license field above.