feat: add support for vLLM Mistral Tokenizer #142
Merged
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Outdated suggestions cannot be applied.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.
fix #141
The vllm
MistralTokenizer
class is a wrapper over the mistral tokenizers frommistral-common
.When the
build_vllm_token_enforcer_tokenizer_data
function is called, the underlyingmistral-common
tokenizer is passed instead of theMistralTokenizer
, which has the proper methods used bylm-format-enforcer
to access the tokens and special tokens of the tokenizer.This MR adds a check to directly pass the vllm
MistralTokenizer
tokenizer instead of the underlyingmistral-common
tokenizer when building the tokenizer data.