llama : optimize long word tokenization with WPM #8034
llama : optimize long word tokenization with WPM
677bf2e9
ggerganov
force pushed
to
677bf2e9
1 year ago
ggerganov
merged
a927b0f3
into master 1 year ago
ggerganov
deleted the gg/max-token-length branch 1 year ago
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub