Skip to main content

Module siglip

Module siglip 

Source
Expand description

SigLIP (Sigmoid Loss for Language-Image Pre-training) Vision Transformer

Implementation based on the timm (PyTorch Image Models) SigLIP architecture. This is a standalone implementation that can be used by multimodal models like Janus.

Architecture:

  • Patch embedding (Conv2d)
  • Position embeddings (learned)
  • Transformer blocks (self-attention + MLP with pre-norm)
  • Final layer norm
  • Optional attention pooling head

Structsยง

SigLIPConfig
Configuration for SigLIP vision encoder
SigLIPVisionTransformer
SigLIP Vision Transformer