Skip to content

encode result 与 Qwen1.5-4B-Chat 模型使用的不一致 #2

Description

@wqtian

Qwen1.5-4B-Chat 也是基于 Tiktoken。相同的字符串 “hello world”, Qwen1.5-4B-Chat 得到的 encoding 结果是 [14990, 1879], 使用你的库得到 [15339, 1917],是哪里出了问题

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions