Skip to content

Models

Every model here is a pure-Keras 3 port with weights converted from the original checkpoints. Pages are grouped by modality and listed alphabetically, and each one follows the same shape: API, preprocessing, variants, a runnable example with its measured output, data format, and how to load fine-tuned weights.

The shared machinery is documented separately, in Main Classes and Configuration.

Text models

Encoders for embeddings and masked language modelling, and decoder LLMs, dense and mixture-of-experts.

Vision models

Detection, segmentation, monocular depth, and self-supervised backbones.

Audio models

Speech recognition, and speech-aware language models that take audio and text together.

Multimodal models

Vision-language encoders, generative VLMs, and grounding across detection, OCR, pointing and referring.