Optimized version of llama3 / gemma.
Project description
llaminate
Optimized version of llama3, using tokun.
This project is a showcase for a new tokenization technique. It uses a NN model to compress the whole Unicode space into tokens.
Resources
Models
Notebooks
TODO
See TODO.
Credits
This project winks at llama3 from Meta, but doesn't actually its weights nor code.
License
Licensed under the aGPLv3.
Project details
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
llaminate-0.0.5.tar.gz
(3.1 kB
view hashes)
Built Distribution
Close
Hashes for llaminate-0.0.5-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | ef75cd5d0a9b7e3e1d1efb69abf8f95bf530efefc2f28e355c42a16cfa98fe21 |
|
MD5 | 9d82d59a958a82e62cb74dcec1a22610 |
|
BLAKE2b-256 | 0e22f559c1e7133cc4333b0ac99cb6745a57d331e18849543e710c80c7407b17 |