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.
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.
Stars
10
Forks
2
Language
Python
License
MIT
Category
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.
Higher-rated alternatives
unslothai/unsloth
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek, Qwen, Llama,...
huggingface/peft
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
modelscope/ms-swift
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.5, DeepSeek-R1, GLM-5,...
oumi-ai/oumi
Easily fine-tune, evaluate and deploy gpt-oss, Qwen3, DeepSeek-R1, or any open source LLM / VLM!
linkedin/Liger-Kernel
Efficient Triton Kernels for LLM Training