Skip to content

GGUF naming convention #13

Description

@mrexodia

There is a naming convention in GGUF files where the [A-Za-z_]+ slug after the last - is the quantization type. Today I tried loading a model from https://huggingface.co/mudler/Step-3.7-Flash-APEX-GGUF where the files are named like this:

Step-3.7-Flash-APEX-Balanced.gguf
Step-3.7-Flash-APEX-Compact.gguf
Step-3.7-Flash-APEX-I-Balanced.gguf
Step-3.7-Flash-APEX-I-Compact.gguf <- I have this one downloaded
Step-3.7-Flash-APEX-I-Mini.gguf
Step-3.7-Flash-APEX-I-Quality.gguf
Step-3.7-Flash-APEX-Quality.gguf

When using llama serve it detected the following model id from my huggingface cache:

mudler/Step-3.7-Flash-APEX-GGUF:COMPACT

If you were to name the files like Step-3.7-Flash-APEX-I_Compact.gguf it would be unambiguous and matching llama.cpp's conventions. The specific issue here is that both -I-Compact and -Compact resolve to :COMPACT and there isn't really a clean way to disambiguate this.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Fields

    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions