Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

> When fine-tuned on public Replit user code, the model outperforms models of much larger size such as CodeLlama7B:

The table just below this shows the other models doing better on half of the benchmarks; the Replit column being in boldface is misleading.



I don't think the boldface is meant to mean "better".

I just thought it was meant to draw attention to their numbers.


The standard is to bold the best figure per column. If none are significantly different you don't bold any generally but it's standard practice to use this to highlight which approach is best in each task.


Agreed this threw me.

I think colouring a column is the common approach to drawing attention to your own while still respecting the best is bold custom, which they've sort of done with the header, but personally I'd have gone with the cell background for the column.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: