michaelnny/QLoRA-LLM

A simple custom QLoRA implementation for fine-tuning a language model (LLM) with basic tools such as PyTorch and Bitsandbytes, completely decoupled from Hugging Face.

34
/ 100
Emerging

This project helps machine learning engineers fine-tune large language models (LLMs) like LLaMA-2 with significantly less GPU memory, without relying on Hugging Face's PEFT library. You input your pre-trained LLM weights and a dataset for fine-tuning, and it outputs a more specialized LLM adapted to your specific tasks. It is for ML engineers and researchers who need granular control over the fine-tuning process or are working with custom LLM architectures.

No commits in the last 6 months.

Use this if you need to fine-tune a large language model with QLoRA for memory efficiency, want to avoid Hugging Face dependencies, and require full control over the underlying training mechanics.

Not ideal if you are looking for a ready-to-use, robust library for production applications or prefer the convenience and broad compatibility of the Hugging Face ecosystem.

large-language-models model-fine-tuning machine-learning-research deep-learning-optimization natural-language-processing
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

10

Forks

2

Language

Python

License

MIT

Last pushed

Jan 29, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/michaelnny/QLoRA-LLM"

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