FreeAIRepo
Training & fine-tuning

sunrainyg/RandOpt

Official Codebase for "Neural Thickets: Diverse Task Experts Are Dense Around Pretrained Weights" (ICML 2026 Spotlight)

Python
Stars
656
Forks
73
Open issues
2
Last push
1mo ago

About RandOpt

RandOpt is a free, open-source machine learning tool by sunrainyg, written mainly in Python. Official Codebase for "Neural Thickets: Diverse Task Experts Are Dense Around Pretrained Weights" (ICML 2026 Spotlight). It has 656 GitHub stars and 73 forks, and was last updated 1mo ago. GitHub doesn't detect a standard license, so check the repository before using it commercially.

License
Not detected
Language
Python
Stars
656
Last update
1mo ago
Runs on Mac
Not stated
GPU
Not stated
Paid API key
Not required
Self-hostable
Yes

Similar free tools

All Training & fine-tuning tools →

RandOpt FAQ

Is RandOpt free?

Yes. RandOpt is open source and free to use. GitHub doesn't detect a standard license, so check the repository before using it commercially.

Does RandOpt run on a Mac?

The project doesn't say. Check its installation guide before you start.

Does RandOpt need a GPU?

The project doesn't state hardware needs. AI models generally run much faster with a GPU.

Is RandOpt still maintained?

It was last updated 1mo ago. Check recent issues on GitHub to judge how active it is.

What are alternatives to RandOpt?

Similar free, open-source tools include pytorch-image-models, ludwig, align-anything, bitsandbytes.

Related topics