kerasformers ports of Google's Gemma 3n on-device multimodal models (image + audio + text), runnable on JAX / PyTorch / TensorFlow.
AI & ML interests
Open-Source AI and ML
Recent Activity
View all activity
Organization Card
kerasformers
KerasFormers: Open-source Keras 3 collection of pretrained models across Vision, LLM, VLM, Depth, Speech, and more
Important
kerasformers is under active development, and we are currently migrating from GitHub-hosted release weights to the Hugging Face Hub. The PyPI package may lag behind the latest models, fixes, and API updates. This migration includes properly typed configuration files and dedicated weights for each model. Until the migration is complete, we recommend installing kerasformers directly from the main branch on GitHub rather than from PyPI.
pip install git+https://github.com/IMvision12/KerasFormers.git
models 665
kerasformers/gemma-3n-e4b-it
Image-Text-to-Text • Updated
kerasformers/gemma-3n-e4b
Image-Text-to-Text • Updated
kerasformers/gemma-3n-e2b-it
Image-Text-to-Text • Updated
kerasformers/gemma-3n-e2b
Image-Text-to-Text • Updated
kerasformers/dinov2-large
Image Feature Extraction • Updated • 24
kerasformers/dinov2-base
Image Feature Extraction • Updated • 40
kerasformers/dinov2-small
Image Feature Extraction • Updated • 34
kerasformers/dinov2-giant
Image Feature Extraction • Updated
kerasformers/dinov3-convnext-large-pretrain-lvd1689m
Image Feature Extraction • Updated • 43
kerasformers/dinov3-convnext-base-pretrain-lvd1689m
Image Feature Extraction • Updated • 49
datasets 0
None public yet