mradermacher

/

model_requests

like 122

HunYuanDenseV1ForCausalLM is not not currently supported by llama.cpp and so thous models would fail to convert to GGUF.

HunYuanDenseV1ForCausalLM is not not currently supported by llama.cpp and so thous models would fail to convert to GGUF.

https://huggingface.co/tencent/Hunyuan-MT-7B/discussions/1

It seems to be a problem with the Hunyuan-MT-7B itself,Hunyuan-MT-Chimera-7B work.

Dear @wqerrewetw and @eleius
We successfully created GGUF quanta of booth Hunyuan-MT-7B and Hunyuan-MT-Chimera-7B.

Convenient download page:

• https://hf.tst.eu/model#Hunyuan-MT-7B-GGUF
• https://hf.tst.eu/model#Hunyuan-MT-Chimera-7B-GGUF

Static quants:

• https://huggingface.co/mradermacher/Hunyuan-MT-7B-GGUF
• https://huggingface.co/mradermacher/Hunyuan-MT-Chimera-7B-GGUF

Weighted/imatrix quants:

• https://huggingface.co/mradermacher/Hunyuan-MT-7B-i1-GGUF
• https://huggingface.co/mradermacher/Hunyuan-MT-Chimera-7B-i1-GGUF