Skip to content

allow option for using the slow tokenizer#2

Merged
snova-jonathanl merged 1 commit intomainfrom
jonathanl/allow_slow_tokenizer
Jul 12, 2024
Merged

allow option for using the slow tokenizer#2
snova-jonathanl merged 1 commit intomainfrom
jonathanl/allow_slow_tokenizer

Conversation

@snova-jonathanl
Copy link
Collaborator

  • Allow for specifying a slow tokenizer for llava_hf models.
  • Default will remain the same (use fast tokenizer).
  • Edit the llava run script template to add fast_tokenizer=False to the pretrained args

Signed-off-by: Jonathan Li <jonathan.li@sambanovasystems.com>
Copy link
Owner

@snova-guhae snova-guhae left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@snova-jonathanl snova-jonathanl merged commit 13a07bf into main Jul 12, 2024
@snova-jonathanl snova-jonathanl deleted the jonathanl/allow_slow_tokenizer branch July 12, 2024 20:34
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.

2 participants