-
Notifications
You must be signed in to change notification settings - Fork 348
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Circumvent Broken llama.cpp Pre-Tokenizer #892
Merged
Merged
Conversation
This file contains 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
RuntimeError: Cannot convert token � (29333) to bytes: �
Using generate()
with models.llamacpp
RuntimeError: Cannot convert token � (29333) to bytes: �
Using generate()
with models.llamacpp
RuntimeError: Cannot convert token � (29333) to bytes: �
Using generate()
with models.llamacpp
01b7390
to
496e0a6
Compare
rlouf
reviewed
May 17, 2024
rlouf
reviewed
May 17, 2024
rlouf
reviewed
May 17, 2024
rlouf
reviewed
May 17, 2024
rlouf
reviewed
May 17, 2024
rlouf
reviewed
May 17, 2024
RuntimeError: Cannot convert token � (29333) to bytes: �
Using generate()
with models.llamacpp
2987784
to
4e84812
Compare
Looks good, thank you for the fix. I think it will be valuable to many people in the community 🙏 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Fixes #820
Problem:
llama.cpp's pre-tokenizer doesn't handle unicode properly (draft PR: ggerganov/llama.cpp#5613). This results in tokens which are incompatible with Outlines byte-wise FSM and causes #820's error.
Solution:
models.llamacpp()
specifies aLlamaHFTokenizer
, populate the vocabulary used in index construction withtokenizer.get_vocab()
. This takes advantage of huggingface's working pre-tokenizer.LlamaHFTokenizer
:Debug Notes / Observations:
29333
(b' \xef\xbf\xbd'
)models.llamacpp
, but notmodels.transformers
AutoTokenizer
'sget_vocab()
is inconsistent with itsencode
/decode
output.get_vocab()[ b'\xc4\xa0\xc3\xaf\xc2\xbf\xc2\xbd'.decode()]
=29333
get_vocab()[ b' \xef\xbf\xbd'.decode()]
->KeyError
encode( b'\xc4\xa0\xc3\xaf\xc2\xbf\xc2\xbd'.decode())
=[144242, 37572, 30182, 26062]
encode(b' \xef\xbf\xbd'.decode())
=[29333]
tokenizer.get_vocab()
has a distinct mapping fromtokenizer.decode
due to the pre-tokenizer: