[mjburgess]

300bn weights, at 4bytes/weight is 1.2TB

[Epa095]

Yes, but how does it remember the stuff you told it earlier in the conversation? Those 1.2TB is the trained model, and I assume that those weights are not changed by the conversation?

[bryan0]

I believe that the previous input, from earlier in the conversation, is always prepended to the new input.