support bpe tokenizer in convert#2228
Merged
ggerganov merged 3 commits intoggml-org:masterfrom Jul 25, 2023
Merged
Conversation
added 2 commits
July 15, 2023 14:12
Signed-off-by: ldwang <ftgreat@gmail.com>
Signed-off-by: ldwang <ftgreat@gmail.com>
Contributor
|
Can you provide test instruction so that I can verify the change? |
Signed-off-by: ldwang <ftgreat@gmail.com>
Contributor
Author
instruction: requirements: |
Contributor
|
Note: Using an llama model with gpt2 tokenizer will be fully supported in the new ggml file format. ggml-org/ggml#302 |
Contributor
Author
Could you please give me the support schedule? |
ggerganov
approved these changes
Jul 25, 2023
This was referenced Jul 27, 2023
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Our released Aquila models used bpe tokenizer, so in convert.py we just add one branch for preprocessing bpe tokenizer vocab into sentencepiece in order to use following modules like inference or int4. we have make sure all encoding ids are all the same and have no impact other modules.
Could you please review this pr, thanks.
Related issue: #2093