Good to see I've made you curious. On this page you'll find interactive demos of projects that you can run to your heart's content. If you have any questions, feel free to message me.
This card showcases an answer localization model: ask any answerable question about a portion of text in natural language, you will see where the answer is located in the text. Unlike Large Language Models (LLMs) such as ChatGPT and LLaMA, this model does not 'hallucinate'. Instead of generating text, it locates the answer within the text that is provided, making the output more consistent and thus more useful for business applications. Furthermore, at 100 MB it is orders of magnitude smaller than the aforementioned models, which makes it possible to run client-side on any smartphone these days. This model works by using a compressed version of BERT for Natural Language Processing (NLP). To run this, (down)load the model of 100 MB (careful if you're on mobile data), then hit the locate button. Feel free to experiment as often as you like with your own questions or even passage.
answer localization
BERT
100 MB