LoicGrobol/zeldarose

Train transformer-based models.

51
/ 100
Established

This tool helps developers efficiently train custom transformer-based language models. You provide raw text files, with one sentence per line, to train both a tokenizer and a transformer model. The output is a trained model and tokenizer that can then be used for various natural language processing tasks. It's designed for machine learning engineers and researchers working with large text datasets.

Available on PyPI.

Use this if you need a straightforward way to train transformer models, especially for masked language modeling, using existing frameworks like Hugging Face's transformers.

Not ideal if you are a beginner looking for a no-code solution or if your primary goal is fine-tuning an existing model without custom pre-training.

natural-language-processing machine-learning-engineering text-analytics language-model-training
Maintenance 10 / 25
Adoption 7 / 25
Maturity 25 / 25
Community 9 / 25

How are scores calculated?

Stars

28

Forks

3

Language

Python

License

Last pushed

Jan 23, 2026

Commits (30d)

0

Dependencies

18

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/LoicGrobol/zeldarose"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.