sdasd112132

/

Vision-8B-MiniCPM-2_5-Uncensored-and-Detailed-4bit

like 26

I used llama.cpp and want to tranfer to GGUF, but I fail, could you please help to upload an gguf file?

(llama) root@gpulan:/home/llama.cpp# python convert_hf_to_gguf.py ./MiniCPM-Uncensored/ --outfile cpm-f16.gguf --outtype f16
INFO:hf-to-gguf:Loading model: MiniCPM-Uncensored
ERROR:hf-to-gguf:Model MiniCPMV is not supported

Many Thanks