Project description

Fuyu

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

Blog paper code

Appreciation

Lucidrains
Agorians
Adept

Install

pip install fuyu

Architecture

image patch embeddings -> linear projection -> decoder llm

License

MIT

Citations

Project details

These details have not been verified by PyPI

Project links

GitHub Statistics

View statistics for this project via Libraries.io, or by using our public dataset on Google BigQuery

Release history Release notifications | RSS feed

0.0.7

Jan 25, 2024

This version

0.0.3

Oct 27, 2023

0.0.2

Oct 19, 2023

0.0.1

Oct 18, 2023

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)

Uploaded Oct 27, 2023 Source

Built Distribution

fuyu-0.0.3-py3-none-any.whl (18.8 kB view hashes)

Uploaded Oct 27, 2023 Python 3

Hashes for fuyu-0.0.3.tar.gz

Hashes for fuyu-0.0.3.tar.gz
Algorithm	Hash digest
SHA256	`18249245ae6bfe043286e4280762a6bbd5e9dd0218efc017e623a7bee7d6bcb0`
MD5	`a80ee8e57d21b92e6f355a3ec3b78efb`
BLAKE2b-256	`52b5917eb54682f258226c33fef64b93e33d06248dcd7090639c20870d4e54dc`

Hashes for fuyu-0.0.3-py3-none-any.whl

Hashes for fuyu-0.0.3-py3-none-any.whl
Algorithm	Hash digest
SHA256	`17e2476f95e72eed5aa82301575942aee8c1d9c431139f60cf0849e8cbb28375`
MD5	`8b3727639c7eadd183d381a8f64fabb8`
BLAKE2b-256	`85fa80ae895767b570874a6ef946dc360d207a8527f24ecdb423355a572da2d4`