Feature Request: Add new model support Hunyuan-A13B

[yeahdongcn]

Prerequisites

• I am running the latest code. Mention the version if possible as well.
• I carefully followed the README.md.
• I searched using keywords relevant to my issue to make sure that I am creating a new issue that is not already open (or closed).
• I reviewed the Discussions, and have a new and useful enhancement to share.

Feature Description

I was trying to convert https://huggingface.co/tencent/Hunyuan-A13B-Instruct to GGUF using gguf-my-repo and it failed with the following error message:

Error converting to fp16: INFO:hf-to-gguf:Loading model: Hunyuan-A13B-Instruct
WARNING:hf-to-gguf:Failed to load model config from downloads/tmpum6omczf/Hunyuan-A13B-Instruct: The repository downloads/tmpum6omczf/Hunyuan-A13B-Instruct contains custom code which must be executed to correctly load the model. You can inspect the repository content at /home/user/app/downloads/tmpum6omczf/Hunyuan-A13B-Instruct .
 You can inspect the repository content at https://hf.co/downloads/tmpum6omczf/Hunyuan-A13B-Instruct.
Please pass the argument `trust_remote_code=True` to allow custom code to be run.
WARNING:hf-to-gguf:Trying to load config.json instead
INFO:hf-to-gguf:Model architecture: HunYuanMoEV1ForCausalLM
ERROR:hf-to-gguf:Model HunYuanMoEV1ForCausalLM is not supported

So I'm wondering whether this new model could be supported in both llama.cpp and gguf-my-repo.

Motivation

The newly introduced Hunyuan-A13B model features a total of 80 billion parameters with 13 billion active parameters. I'd like to convert it to GGUF and serve it in llama.cpp.

Possible Implementation

No response

[yeahdongcn]

#14415