Skip to content

Specify max tokens or alternate way to constrain response from Ollama models #579

@gjreda

Description

@gjreda

llama2 can produce some extremely long chat responses

Metadata

Metadata

Assignees

No one assigned

    Labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions