juzhengz/LoRI
[COLM 2025] LoRI: Reducing Cross-Task Interference in Multi-Task Low-Rank Adaptation
This tool helps AI developers fine-tune large language models (LLMs) more efficiently when working with multiple tasks simultaneously. It takes a base LLM (like LLaMA-3-8B or Mistral-7B) and task-specific datasets, then produces specialized "adapters" that allow the model to perform well on tasks like code generation, mathematical reasoning, or safety alignment without tasks interfering with each other. AI/ML engineers and researchers who build and deploy LLMs for diverse applications would use this.
171 stars. No commits in the last 6 months.
Use this if you need to fine-tune a large language model for several distinct tasks and want to avoid performance degradation or "forgetting" on one task when training for another.
Not ideal if you are working with single-task fine-tuning or do not have the technical expertise in deep learning model development.
Stars
171
Forks
14
Language
Python
License
—
Category
Last pushed
Jul 08, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/juzhengz/LoRI"
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.