FEAT: added a ChatMessageNormalizer that formats messages in the template specified by a Hugging Face tokenizer #128
Conversation
This file contains 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
…pecified by a Hugging Face tokenizer
…ferent Hugging Face tokenizers
romanlutz
approved these changes
Mar 29, 2024
…_message notebook
rlundeen2
approved these changes
Mar 29, 2024
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Outdated suggestions cannot be applied.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.
Description
I added a chat message normalizer called
ChatMessageNormalizerTokenizerTemplate, which takes a Hugging Face tokenizer as input and allows you to convert a list of chat messages into the format specified by that tokenizer. This might be the ChatML format (which @dlmgary created a custom normalizerChatMessageNormalizerChatMLfor) or some other custom format that was used to train the model.Tests and Documentation
I added tests to demonstrate that the normalizer works on three different Hugging Face tokenizers and some example usage to the
chat_message.ipynbdemo notebook.