NVlabs/EoRA

[ICLRW'26] EoRA: Fine-tuning-free Compensation for Compressed LLM with Eigenspace Low-Rank Approximation

45
/ 100
Emerging

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.

LLM deployment Model compression Deep learning optimization AI efficiency NLP applications
No Package No Dependents
Maintenance 13 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

29

Forks

3

Language

Python

License

Category

llm-fine-tuning

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.