Rust - Fix Serialization when tokens are part of original vocab #315
Conversation
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
chris-ha458
added a commit
to chris-ha458/tokenizers
that referenced
this pull request
Aug 9, 2023
Narsil
pushed a commit
that referenced
this pull request
Aug 10, 2023
* CD backports follow huggingface/safetensors#317 * fix node bindings? `cargo check` doesnt work on my local configuration from `tokenizers/bindings/node/native` i don't think it will be a problem but i have difficulty telling * backport #315 * safetensors#317 back ports
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Outdated suggestions cannot be applied.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.
When we add only special tokens, which are all parts of the original vocabulary,
self.added_tokens_map.len()was 0, leading to a weird serialization.For example, for Bert it was producing:
[],{"id":0,"special":true,"content": ...