Dream 7B #12017

Model/Pipeline/Scheduler description

https://hkunlp.github.io/blog/2025/dream/

In short, Dream 7B:

• consistently outperforms existing diffusion language models by a large margin;
• matches or exceeds top-tier Autoregressive (AR) language models of similar size on the general, math, and coding > abilities;
• demonstrates strong planning ability and inference flexibility that naturally benefits from the diffusion modeling.

Basically a new SotA diffusion-based LLM. It would be great to introduce LLMs to the library's roster.

Open source status

• The model implementation is available.
• The model weights are available (Only relevant if addition is not a scheduler).

Provide useful links for the implementation

Team: Jiacheng Ye*, Zhihui Xie*, Lin Zheng*, Jiahui Gao*, Zirui Wu, Xin Jiang, Zhenguo Li, and Lingpeng Kong.
Affiliations: The University of Hong Kong, Huawei Noah’s Ark Lab

Base HF Link
Instruction-tuned HF Link
Codebase