could please tell some detail about how to quantization the qwen-image models
#11
by
dzfancy
- opened
hi bro
i am a beginer of llm,aand i am using llama.cpp but failed to convert the qwen-image model
here is the code
python llama.cpp/convert_hf_to_gguf.py /home/featurize/.cache/modelscope/hub/models/Qwen/Qwen-Image --outfile qwen-image.gguf --outtype f16
the error is
FileNotFoundError: [Errno 2] No such file or directory: '/home/featurize/.cache/modelscope/hub/models/Qwen/Qwen-Image/config.json'
could you tell me how can i quantize the qwen-image model?
thanks a lot
https://github.com/city96/ComfyUI-GGUF/tree/auto_convert/tools
try the tool_auto.py, for me i had to do the llama.cpp patching manually but it works.