model_213644317_clip_xlarge.py

Model Overview

A xlarge-scale implementation of the clip architecture, built for retrieval tasks.

Architecture

• Architecture: clip
• Scale: xlarge
• Attention: dilated
• Fusion strategy: low rank
• Task head: retrieval
• Activation: swish
• Normalization: rmsnorm
• Initialization: kaiming

Training

• Optimizer: adamw
• LR scheduler: constant warmup

Files

• model_213644317_clip_xlarge.py — main artifact of this repository

License

See the license field above.