Skip to content

HF tokenizers (on the training side)#5

Merged
TevenLeScao merged 1 commit intomainfrom
hf-tok-training-time
Jul 20, 2021
Merged

HF tokenizers (on the training side)#5
TevenLeScao merged 1 commit intomainfrom
hf-tok-training-time

Conversation

@TevenLeScao
Copy link
Copy Markdown
Collaborator

This allows the user to use HF tokenizers at training time, using the same preprocessing-time arguments as #2

@TevenLeScao TevenLeScao merged commit 0b2f0df into main Jul 20, 2021
@jaketae jaketae deleted the hf-tok-training-time branch August 24, 2021 19:10
adammoody referenced this pull request in adammoody/Megatron-DeepSpeed Dec 20, 2021
improve DS integration docs + evaluation + logging
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant