Misc. bug: cannot convert GLM-4-9B-Chat (glm-4-9b-chat-hf) to GGUF format

[MoonRide303]

Name and Version

.\llama-cli.exe --version
version: 4491 (c67cc98)
built with MSVC 19.39.33523.0 for x64

Operating systems

Windows

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

Python/Bash scripts

Command line

python convert_hf_to_gguf.py --outtype f16 ..\glm-4-9b-chat-hf\ --outfile glm-4-9b-chat-hf-F16.gguf

Problem description & steps to reproduce

Despite ChatGLM4-9b being marked as supported attempt to convert GLM-4-9B-Chat model (glm-4-9b-chat-hf, command above) to GGUF format fails, with the following error:

INFO:hf-to-gguf:Loading model: glm-4-9b-chat-hf
ERROR:hf-to-gguf:Model GlmForCausalLM is not supported

First Bad Commit

No response

Relevant log output

[arch-btw]

The transformers/hf-only version hasn't been added yet, please see last 2 comments here: #10573

For now the only one that works is the same model but slightly different in that it isn't a pure transformers implementation:

https://huggingface.co/THUDM/glm-4-9b-chat

[github-actions]

This issue was closed because it has been inactive for 14 days since being marked as stale.