[qxfys]

How do you pick which one should be 2, which one should be 4, etc. Is this secret sauce? or, something open?

[danielhanchen]

Oh I wrote about it here: https://docs.unsloth.ai/basics/unsloth-dynamic-2.0-ggufs We might provide some scripts for them in the future!

[qxfys]

Thanks! But, I can't find any details on how you "intelligently adjust quantization for every possible layer" from that page. I assume this is a secret?

I am wondering about the possibility that different use cases might require different "intelligent quantization", i.e., quantization for LLM for financial analysis might be different from LLM for code generation. I am currently doing a postdoc in this. Interested in doing research together?