I'm wondering when everyone will transition from tracking parameter count vs evaluation metric to (total gpu RAM + total CPU RAM) vs evaluation metric.
For example, a 7B parameter model using float32s will almost certainly outperform a 7B model using float4s.
Additionally, all the examples of quantizing recently released superior models to fit on one GPU doesnt mean the quantized model is a "win." The quantized model is a different model, you need to rerun the metrics.
> The model requires ~264GB of RAM
I'm wondering when everyone will transition from tracking parameter count vs evaluation metric to (total gpu RAM + total CPU RAM) vs evaluation metric.
For example, a 7B parameter model using float32s will almost certainly outperform a 7B model using float4s.
Additionally, all the examples of quantizing recently released superior models to fit on one GPU doesnt mean the quantized model is a "win." The quantized model is a different model, you need to rerun the metrics.