Refined (v5.3) update

Fix with the correct model files

Refined (v5.1) update

Major (v5) training update

Readme and tokeniser update

Fourth iteration with 1.9 million training records

Pre-v4 readme and support files update

Major update with 1.6 million training records

Updated the readme

Updated the readme and get_data.sh, and added a requirements file

Delete src/data/clean_corpus.jsonl

Delete src/data/kkwiki-latest-pages-articles.xml.bz2

Delete src/data/kazakh_latin_corpus.jsonl

Minor update to the "get_data.sh" file

Minor update to the get_data.sh file

Training update with more data and 2 epochs

Fixed character mapping, training with 8 epochs

Major training update

Upload folder using huggingface_hub