So has anyone tried to you know for example keep constant weights base model and just transmit the data, might be better compression

I might be confused by the question, but I overfit the model on a single file and then transport the model along with the arithmetic coding file. There have been ideas where you generalize a model (constant weights) and then pass the arithmetic coding file along with it. So that way you only pass the arithmetic coding file.

BUT my model size is just 900KB (for 100mb file atleast) so it is negligible