UCDvision/NOLA
Code for NOLA, an implementation of "nola: Compressing LoRA using Linear Combination of Random Basis"
This project helps machine learning practitioners fine-tune large models, like LLMs and Vision Transformers, using significantly fewer parameters and less GPU memory. It takes a pre-trained large model and a small dataset for fine-tuning, outputting a more compact, fine-tuned model without losing accuracy. Data scientists, AI researchers, and machine learning engineers who work with large language models or computer vision models would use this.
No commits in the last 6 months.
Use this if you need to fine-tune massive AI models efficiently, especially when computational resources or model deployment size are critical concerns.
Not ideal if you are working with smaller models where parameter count and memory footprint are not major obstacles.
Stars
57
Forks
4
Language
Python
License
MIT
Category
Last pushed
Aug 25, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/UCDvision/NOLA"
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