build GGUF file
how to build the ChatTS-14B project to GGUF file ?
transfer to error message for:
root@comfy-ui:/data/llama.cpp/llama.cpp# python3 convert_hf_to_gguf.py --outfile /data/ChatTS-14B.gguf /data/huggingface-repository/ChatTS-14B/
INFO:hf-to-gguf:Loading model: ChatTS-14B
INFO:hf-to-gguf:Model architecture: Qwen2TSForCausalLM
ERROR:hf-to-gguf:Model Qwen2TSForCausalLM is not supported
how to solve this error?
"how to solve this error?"
Someone should implement the quantization for this model Architecture in llama.cpp
Sorry for the late reply.
llama.cpp currently does not support the ChatTS model architecture, so you cannot convert it to the gguf format. If you need to deploy it locally, please refer to the vllm deployment of ChatTS.
that's great,i just go to get it
Sorry for the late reply.
llama.cpp currently does not support the ChatTS model architecture, so you cannot convert it to the gguf format. If you need to deploy it locally, please refer to the vllm deployment of ChatTS.
i'll hope to format of GGUF