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

The next token is taken by sampling the logits in the final column after unembedding. But isn't that just the last token again? Or is the matrix resized to N+1 at some step?


There is an end-of-sequence token appended to the input sequence, and this is what is transformed into the predicted next token.




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

Search: