apple/ml-ferret
Multimodal model for referring and grounding at any granularity
View on index · View in 3D Map
Related repos
- Open-source multimodal model for scientific tasks
- Toolkit for fine-tuning and training large language and vision models
- Framework for robot manipulation using vision and language models
- Survey of unified multimodal models
- library for training large models across any modality, config-driven and modular, from Apple Research
- unified multimodal model for both understanding and generating images and text
- Multimodal LLM inference engine for mobile devices
- developer cheat sheets collection, quick references for coding
- fast vision-language model for on-device AI
- Vision-Language-Action foundation model for robot control
