Introducing the first discrete diffusion pipeline for text in Diffusers -- LLaDA2 by @TheInclusionAI π₯
It follows an MoE architecture w/ 16B total params. It is definitely not SOTA across the board, but it hopefully flips that soon.
Check out the links below to know more β¬οΈ

@krasul shipped it in this PR:
github.com/huggingface/diβ¦
The docs are available here:
huggingface.co/docs/diffusersβ¦
Supported models:
* inclusionAI/LLaDA2.1-mini
* inclusionAI/LLaDA2.1-flash
github.com/huggingface/diβ¦
The docs are available here:
huggingface.co/docs/diffusersβ¦
Supported models:
* inclusionAI/LLaDA2.1-mini
* inclusionAI/LLaDA2.1-flash
Generated by Thread Navigator
Press β + S to quick-export
