News for hackers. Stuff that matters.
Re:Show HN: Cedille, the largest French language model, rele... by jhgb on Wednesday November 10, 2021 @08:10PM (#29183246)
I'm speaking in generic terms, of course. All models should be at the very least unbiased, though -- that's the least demand you can make of them (and generally an easy one to check, compared to other properties, such as having minimum variance of all possible models and such.)
Re:Show HN: Cedille, the largest French language model, rele... by skybrian on Wednesday November 10, 2021 @08:18PM (#29183311)
I sort of agree in principle but I’m not sure what unbiased means for a language model or how you would measure it, so this doesn’t sound all that easy to me.