Different LLM has different set of tokenizers. To streamline the token calculation method on our platform, it's best to develop our own set of tokenisers.
Reference: https://github.com/huggingface/tokenizers
Please authenticate to join the conversation.
PRD in Progress
π‘ Request a feature
Almost 2 years ago

Shuwei Li
Get notified by email when there are changes.
PRD in Progress
π‘ Request a feature
Almost 2 years ago

Shuwei Li
Get notified by email when there are changes.