hqq icon indicating copy to clipboard operation
hqq copied to clipboard

Hqq vs gguf

Open blap opened this issue 1 year ago • 3 comments

Is there an easy way to convert gguf to hqq and vice-versa? Any comparisons? https://github.com/leafspark/AutoGGUF

blap avatar Sep 13 '24 22:09 blap

Hi! What of quantization is GGUF using? If it's asymmetric quantization (with both scales/zeros) it could be converted

mobicham avatar Sep 14 '24 09:09 mobicham

Hi! What of quantization is GGUF using? If it's asymmetric quantization (with both scales/zeros) it could be converted

Sorry. I don't know the specs, but here you can see details about it and how to convert hf to gguf from llama.cpp: https://github.com/ggerganov/llama.cpp/tree/master/gguf-py

blap avatar Sep 14 '24 13:09 blap

Thanks for sharing, looks like the logic is quite different, so I don't think both quantized outputs are compatible unfortunately.

mobicham avatar Sep 14 '24 16:09 mobicham