No project description provided
Project description
Hippogriff
This repository implements Hawk and Griffin blocks from Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models using Accelerated Scan and Flash Attention for PyTorch.
pip install hippogriff
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
hippogriff-0.0.2.tar.gz
(1.2 MB
view details)
Built Distribution
File details
Details for the file hippogriff-0.0.2.tar.gz.
File metadata
- Download URL: hippogriff-0.0.2.tar.gz
- Upload date:
- Size: 1.2 MB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.0.0 CPython/3.12.2
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | c54c1417a840b1a0e1dd8fb89189866d4b6262ad9647434bdbd5247e1b59353d |
|
| MD5 | d3380f80cbd9e54326ffead7d84682f3 |
|
| BLAKE2b-256 | 3a86bac0587540631dd37017e02e512fa65274293f38415dfd09cfe428a9cde2 |
File details
Details for the file hippogriff-0.0.2-py3-none-any.whl.
File metadata
- Download URL: hippogriff-0.0.2-py3-none-any.whl
- Upload date:
- Size: 4.6 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.0.0 CPython/3.12.2
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | c69bdec57a65e2fc4b214f195e33b23ddb6abcbe063b58752e6b991e11e05d43 |
|
| MD5 | 6b8414fbcaa8a1a12017a4eb3970dd4e |
|
| BLAKE2b-256 | 5a99f065a5fd10b141ee5c561b47a67dcc7b7efeae335ee22cfea52239e9063f |
