Skip to content

Tokenizer for Claude models #177

@xingdi-eric-yuan

Description

@xingdi-eric-yuan

The current way of trimming strings and messages are quite hacky, partly because we don't have access to Claude's tokenizer (we do for OAI models). Once we find good tokenizers for claude models, we will need to revisit the trimming functions.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions