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
When running scripts/two_layers_e2e/navigate.sh, I get:
FileNotFoundError: [Errno 2] No such file or directory: './data/bb_minus_bbh/navigate.json'
should we add path to data as ../../data assuming the user ran setup_data.sh from the root of the repo?