[Issue #820] Cannot convert token � (29333) to bytes: � for some model vocabularies when using llama.cpp #890
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Outdated suggestions cannot be applied.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.
Attempt at solving issue #820 - RuntimeError: Cannot convert token � (29333) to bytes: �
With additional characters in the
gpt2_bytes_to_unicode()
map, I don't get errors anymore.However, it doesn't seem good to add ad-hoc characters like that. We should test on many more kinds of tokenizers.
Benchmarks pass:
Side note: Had to switch to Linux for development because of the
vllm
dependency, see their Requirements.