ZinYY/TreeLoRA
A pytorch implementation of the paper "TreeLoRA: Efficient Continual Learning via Layer-Wise LoRAs Guided by a Hierarchical Gradient-Similarity Tree".
This project helps machine learning engineers and researchers efficiently update large language models (LLMs) with new information without forgetting previous knowledge. You input a pre-trained LLM and new datasets, and it outputs an LLM that has learned the new tasks while retaining its original capabilities. This is ideal for AI practitioners maintaining LLMs in rapidly changing domains.
347 stars.
Use this if you need to continually train Large Language Models on new data and tasks without experiencing 'catastrophic forgetting' of previously learned information.
Not ideal if you are looking for a simple plug-and-play solution for basic LLM fine-tuning or do not have a strong understanding of continual learning concepts.
Stars
347
Forks
63
Language
Python
License
—
Category
Last pushed
Dec 15, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/ZinYY/TreeLoRA"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
OptimalScale/LMFlow
An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.
adithya-s-k/AI-Engineering.academy
Mastering Applied AI, One Concept at a Time
jax-ml/jax-llm-examples
Minimal yet performant LLM examples in pure JAX
young-geng/scalax
A simple library for scaling up JAX programs
riyanshibohra/TuneKit
Upload your data → Get a fine-tuned SLM. Free.