ruimalheiro/training-custom-llama

Llama-style transformer in PyTorch with multi-node / multi-GPU training. Includes pretraining, fine-tuning, DPO, LoRA, and knowledge distillation. Scripts for dataset mixing and training from scratch.

43
/ 100
Emerging

This project helps machine learning engineers and researchers train custom large language models (LLMs) from scratch or fine-tune existing ones. You can input various text datasets and configuration settings, then output a specialized LLM ready for deployment. It's designed for individuals and teams working with large-scale NLP tasks and requiring high-performance computing.

Use this if you need to build or adapt a Llama-style language model using your own datasets and require multi-node or multi-GPU training capabilities.

Not ideal if you're looking for a low-code solution to apply pre-trained models without needing to customize architecture, training methods, or manage distributed computing infrastructure.

Large Language Models NLP Model Training Distributed Machine Learning AI Research Custom Model Development
No Package No Dependents
Maintenance 10 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 11 / 25

How are scores calculated?

Stars

21

Forks

3

Language

Python

License

Apache-2.0

Last pushed

Mar 10, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/ruimalheiro/training-custom-llama"

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