divelab

/

Qwen3-4B-a2d-init

like 1

Follow

DIVE Lab, Texas A&M University 14

Hi, I'm Niels from the Hugging Face community science team.

This PR improves the model card for this repository by:

• Adding relevant metadata (pipeline tag, license, and base model).
• Linking the model to the research paper "Data-Efficient Autoregressive-to-Diffusion Language Models via On-Policy Distillation".
• Adding links to the official project page and GitHub repository.
• Including a BibTeX citation for the work.

This helps users understand the context of this specific artifact (an A2D-converted initialization) and find the associated training and evaluation code.