This is a custom quant of
deepseek-ai/DeepSeek-R1-0528 that has the following:
The idea being that given the huge size of the FFN tensors compared to the rest of the tensors in the model, it should be possible to achieve a better quality while keeping the overall size of the entire model smaller compared to a similar naive quantization.
This is derived from the quant provided by
AesSedai with additional keys added for expert group selection.
