fuyu - Pytorch
Project description
Fuyu
A implementation of Fuyu, the multimodal AI model from Adept in pytorch using a ultra powerful Zeta native decoder with qk_norm, multi grouped query attn, scaled rotary pos embeddings, and a kv_cache
Appreciation
- Lucidrains
- Agorians
- Adept
Install
pip install fuyu
Architecture
image patch embeddings -> linear projection -> decoder llm
License
MIT
Citations
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
fuyu-0.0.3.tar.gz
(18.5 kB
view hashes)
Built Distribution
fuyu-0.0.3-py3-none-any.whl
(18.8 kB
view hashes)