Vocab size differ between tokenizer config and the lm_head

#72

by bonni93 - opened Jun 17

Jun 17

As per the title - the lm_head has a different vocab size wrt the loaded tokenizer.
Why is that the case?

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment