model_213005926_clip_xlarge.py

Model Overview

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

Architecture

• Architecture: clip
• Scale: xlarge
• Attention: grouped query
• Fusion strategy: tensor fusion
• Task head: multitask
• Activation: mish
• Normalization: rmsnorm
• Initialization: xavier uniform

Training

• Optimizer: sgd
• LR scheduler: cosine

Files

• model_213005926_clip_xlarge.py — main artifact of this repository

License

See the license field above.