Isaacus

All

5 repositories

semchunk
Public
A fast, lightweight and easy-to-use Python library for splitting text into semantically meaningful chunks.
python nlp text splitting chunking text-chunking text-splitting semantic-chunking isaacus
Python
•
MIT License
•15•245•2•1•Updated Feb 18, 2025Feb 18, 2025
open-australian-legal-corpus-creator
Public
The code used to create and update the Open Australian Legal Corpus, the first and only multijurisdictional open corpus of Australian legislative and judicial documents.
law legal scraping corpus australia open-data dataset web-scraping datasets isaacus
Python
•
MIT License
•11•80•0•0•Updated Aug 8, 2024Aug 8, 2024
terge
Public
An easy-to-use Python library for merging PyTorch models.
machine-learning ai deep-learning models transformers merge torch pytorch merging model-merging
Python
•
MIT License
•0•8•0•0•Updated Jun 13, 2024Jun 13, 2024
emubert-creator
Public
The training code behind EmuBert, the largest open-source masked language model for Australian law.
nlp training law legal model models transformers australia bert llm
Python
•
MIT License
•0•3•0•0•Updated Jun 2, 2024Jun 2, 2024
open-australian-legal-embeddings-creator
Public
The code used to create and update the Open Australian Legal Embeddings, the first open-source embeddings of Australian legislative and judicial documents.
nlp law legal transformers australia embeddings open-data dataset datasets isaacus
Python
•
MIT License
•3•7•0•0•Updated Feb 17, 2024Feb 17, 2024