Fix and improvements for demo.

microsoft / deep-language-networks

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

MIT License

91 stars 13 forks source link

Fix and improvements for demo. #31

Closed MarcCote closed 9 months ago

MarcCote commented 9 months ago

Allow to specify multiple paths to load log files from. Fix issue where we only show steps for which we have examples.

matheper commented 9 months ago

LGTM. Thanks for fixing and improving the demo!