model_220605654_clip_giant.py

Model Overview

A giant-scale implementation of the clip architecture, built for generation tasks.

Architecture

• Architecture: clip
• Scale: giant
• Attention: flash
• Fusion strategy: low rank
• Task head: generation
• Activation: approx gelu
• Normalization: batchnorm
• Initialization: kaiming

Training

• Optimizer: lamb
• LR scheduler: exponential

Files

• model_220605654_clip_giant.py — main artifact of this repository

License

See the license field above.