Skip to content

Misc. bug: gguf-new-metadata and gguf-editor-gui changes all integer arrays to INT32 #13557

Open
@CISC

Description

@CISC

Name and Version

all

Operating systems

No response

Which llama.cpp modules do you know to be affected?

Other (Please specify in the next section)

Command line

gguf-new-metadata --general-name "foo" nomic-embed-text-v2-moe.Q8_0.gguf nomic-test.gguf

Problem description & steps to reproduce

Dump of the model before editing:

38: [UINT8]    |   237539 | tokenizer.ggml.precompiled_charsmap = [0, 180, 2, 0, 0, 132, ...]

Dump after editing:

38: [INT32]    |   237539 | tokenizer.ggml.precompiled_charsmap = [0, 180, 2, 0, 0, 132, ...]

See #13534

First Bad Commit

No response

Relevant log output

Metadata

Metadata

Assignees

Labels

bugSomething isn't working

Type

No type

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions