Pinned Loading

1. isaacus-dev/semchunk isaacus-dev/semchunk Public

   A fast, lightweight and easy-to-use Python library for splitting text into semantically meaningful chunks.

   Python 648 41

2. isaacus-dev/open-australian-legal-corpus-creator isaacus-dev/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.

   Python 122 20

3. isaacus-dev/mleb isaacus-dev/mleb Public

   The code used to evaluate embedding models on the Massive Legal Embedding Benchmark (MLEB).

   Python 39 6

4. orjsonl orjsonl Public

   A lightweight, high-performance Python library for parsing jsonl files.

   Python 54 6

5. persist-cache persist-cache Public

   An easy-to-use Python library for lightning-fast persistent function caching.

   Python 18 3

6. isaacus-dev/terge isaacus-dev/terge Public

   An easy-to-use Python library for merging PyTorch models.

   Python 12 1