NVlabs/EoRA
[ICLRW'26] EoRA: Fine-tuning-free Compensation for Compressed LLM with Eigenspace Low-Rank Approximation
EoRA helps machine learning engineers and researchers deploy large language models (LLMs) more efficiently by making compressed models perform better without extensive retraining. You provide a pre-compressed LLM, and it outputs an enhanced version that has improved accuracy on specific tasks, while also running faster and using less memory. This is ideal for those managing LLMs in resource-constrained environments.
Use this if you need to recover the accuracy of a compressed large language model quickly, without the time and computational cost of fine-tuning.
Not ideal if you are working with uncompressed models or if your primary goal is to train a new model from scratch rather than enhance an existing compressed one.
Stars
29
Forks
3
Language
Python
License
—
Category
Last pushed
Mar 16, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/NVlabs/EoRA"
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.