Guide-GRPO

Public

Aims for memory-efficient training (24GB VRAM) on consumer GPUs. Optimizing language models through guidance tokens in reasoning chains, based on DeepSeekRL-Extended.

Creat：2025-02-23T18:37:40

Update：2025-03-06T11:11:08

Stars

Stars Increase

Related projects

Build Your Own X

Hot

awesome-list

Master programming by recreating your favorite technologies from scratch.

405936

4个月前

+340today

Awesome

Hot

awesome

? Awesome lists about all kinds of interesting topics

387748

4个月前

+492today

Awesome Selfhosted

Hot

awesome

A list of Free Software network services and web applications which can be hosted on your own servers

239598

4个月前

+193today

Tensorflow

deep-learning

An Open Source Machine Learning Framework for Everyone

191001

1年前

+37today

Computer Science

Hot

awesome-list

? Path to a free self-taught education in Computer Science!

189112

4个月前

+85today

The Book Of Secret Knowledge

Hot

awesome

A collection of inspiring lists, manuals, cheatsheets, blogs, hacks, one-liners, cli/web tools and more.

180375

5个月前

+157today

AutoGPT

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

177399

5个月前

+44today