How to control the length

[gwang-kim]

In the paper, the length of the generated sentence can be controlled without a classifier. How can we do this? Could you give us a detailed explanation or implementation for this?

Best,

Gwanghyun

[XiangLi1999]

Hi, I think you can control length by running ''' python python scripts/infill.py --model_path {path-to-diffusion-lm} --evaltask 'length' --tgt_len [your target length] --use_ddim True --eta 1. --verbose pipe '''