awilliamson10/clipora

Clipora is a powerful toolkit for fine-tuning OpenCLIP models using Low Rank Adapters (LoRA).

29
/ 100
Experimental

Clipora helps machine learning engineers efficiently customize OpenCLIP models for specific image and text understanding tasks. It takes an existing OpenCLIP model and applies Low Rank Adapters (LoRA) to adapt it to new data, producing a specialized model. This is ideal for ML practitioners working with large vision-language models who need to fine-tune them without extensive computational resources.

No commits in the last 6 months.

Use this if you are an ML engineer or researcher needing to fine-tune large OpenCLIP models on custom datasets without retraining the entire model from scratch.

Not ideal if you need a ready-to-use solution for model inference or merging adapters, as these features are not yet fully implemented.

machine-learning-engineering computer-vision natural-language-processing model-fine-tuning deep-learning
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 7 / 25

How are scores calculated?

Stars

24

Forks

2

Language

Python

License

MIT

Last pushed

Aug 15, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/awilliamson10/clipora"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.