In the ARM model, we can set the beam size to generate K candidates in parallel. However, how can we sample the top K candidates in LLaDA? Is the only way to achieve this by performing the forward process K times?
AI Analysis
This issue appears to be discussing a feature request or bug report related to the repository. Based on the content, it seems to be still under discussion. The issue was opened by djx2726889 and has received 0 comments.
Add a comment
Comment form would go here