model_203460895_clip_base.py

Model Overview

A base-scale implementation of the clip architecture, built for contrastive tasks.

Architecture

  • Architecture: clip
  • Scale: base
  • Attention: grouped query
  • Fusion strategy: gated fusion
  • Task head: contrastive
  • Activation: mish
  • Normalization: batchnorm
  • Initialization: trunc normal

Training

  • Optimizer: sgd
  • LR scheduler: linear warmup

Files

  • model_203460895_clip_base.py — main artifact of this repository

License

See the license field above.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support