convert : fix handling of added tokens #3405
Closed
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Outdated suggestions cannot be applied.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.
Some models, like MPT and GPT-NeoX, have spaces in added_tokens: mpt-7b tokenizer.json, gpt-neox-20b tokenizer.json
I have changed the byte decoding to not decode added tokens. I'm not sure what the original KeyError handler was meant to do, as it references multibyte characters, but I have not seen them in practice - just spaces.
See also: huggingface/transformers#1133