We view Large Language Models as stochastic language layers in a network, where the learnable parameters are the natural language prompts at each layer. We stack two such layers, feeding the output of one layer to the next. We call the stacked architecture a Deep Language Network - DLN
LGTM! My only question is whether we add the task description to Leopard datasets or not. If we decide to do so, I am happy to merge the PR.