Skip to content

<|im_end|> causing generation to terminate prematurely #64

Description

@WWaveDragon

Hello! I noticed that the model reads the chat_template during evaluation. For models like GLM-5.2 that use <|im_end|> as an end-of-sequence (EOS) token, mentioning chat_template during its thinking/reasoning phase will leads it to generate <|im_end|>, causing generation to terminate prematurely.

How do you evaluate models that use <|im_end|> as an EOS token, such as Kimi and GLM?

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