Module paligemma 

Multimodal multi-purpose model combining Gemma-based language model with SigLIP image understanding

See PaLiGemma details at:

• Paper
• Google Blog Post

The model is a multimodal combination of:

• SigLIP vision encoder
• Gemma language model
• Cross-projection layers

References:

• HuggingFace Implementation
• Paper: PaLI-3 and Beyond: Scaling Language-Image Learning

Structs

Config

Model

MultiModalProjector