Some folks are claiming there's something funky going on with GGUF quanting for Llama 3 models. I don't disagree.
Some of those people are speculating that it has something to do with converting the raw weights from bf16 to fp16 instead of converting to fp32 as an intermediate step. I think that's bollocks. There is no logical or mathmatical justification for how that could possibly matter.
So to test this crazy theory, I downloaded Undi95/Meta-Llama-3-8B-Instruct-hf and converted it to GGUF three ways:
- fp16 specifically with
--outtype f16 - fp32 specifically with
--outtype f32 - "Auto" with no outtype specified
I then quantized each of these conversions to Q4_K_M and ran perplexity tests on everything using my abbreviated wiki.short.raw text file
The results:
As you can see, converting to fp32 has no meaningful effect on PPL compared to converting to fp16. There will no doubt be some people who will claim "PpL iSn'T gOoD eNoUgH!!1!". For those people, I have uploaded all GGUFs used in this test. Feel free to use those files to do more extensive testing on your own time. I consider the matter resolved until somebody can conclusively demonstrate otherwise.