how convert hf to gguf?
can you tell me how convert hf to gguf please? I want to try it on my RTX4080*4. llama.cpp need add a new model architecture，but It's too hard.
you could try to use the convertor(s) inside gguf-node
ok thank you!
Hello, I found that the convertor also doesn't support Wan2.1-t2v-1.3b convert to gguf
you should use the convertor zero (without screening); convertor alpha is working for flux and sd1-3.5 with architecture screening; t2v-1.3b can be converted but the output file is not working since it was a compressed file already; the conversion process might break the working tensors; you might need to manually add it back but turning out the file size might possibly larger than the safetensors file; that's why not every model file is needed or suitable to convert to gguf; if the smaller file size and memory saving outcome are not achieved then all the conversion effort might become meaningless/worthless in that case
oh，i see，thank you very much