Conversation
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
Contributor
|
[For maintainers] Suggested jobs to run (before merge) run-slow: apertus, auto, bart, bigbird_pegasus, blenderbot, blenderbot_small, blip, blt, bridgetower, chameleon, clipseg, decision_transformer, dia, evolla, flaubert, gemma3n |
itazap
force-pushed
the
fix_nativ_tok
branch
from
5543a1b to
a470031
Compare
itazap
force-pushed
the
fix_nativ_tok
branch
from
d1f5398 to
9601540
Compare
|
Thanks @itazap, when do you think this could be merged? |
Merged
Collaborator
Author
|
Hello! Sorry actually this requires #42894 as the fix! will be merged in the next couple days |
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
3 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
fixes #42796
Fixes incorrect tokenization for Ministral-3 models by preserving and restoring the ByteLevel decoder from tokenizer.json when loading tokenizers. Also custom
initmethods were overwriting the ByteLevel decoder with a Metaspace decoder.Happens because these models reference a
LlamaTokenizerFastin theirtokenizer_config.jsonon the hub. and LlamaTokenizer's init overrides tokenizer components