adamcoscia / knowledgevis

Visually compare fill-in-the-blank LLM prompts to uncover learned biases and associations!

Hey, I'm Adam! 👋

💻 I design and develop visual analytics systems to help people understand complex data, mitigate biases, and make decisions. My tools have been used by researchers, scientists and engineers for analyzing and interpreting large language models (LLMs) 🤖, guiding deep ocean expeditions 🌊 and enabling scientist-guided spacecraft autonomy 🚀

🌱 I'm currently a Human-Centered Computing PhD student at Georgia Tech. I work with Alex Endert as a member of the Visual Analytics Lab.

💞️ I've collaborated with incredible designers, engineers, scientists, and researchers at Vanderbilt, Georgia State, Tufts, Emory, Caltech, ArtCenter, Monterey Bay Aquarium Research Institute (MBARI), and NASA Jet Propulsion Laboratory (JPL).

| 🪪 My Website | 📜 Google Scholar | 🤝 LinkedIn | 🐦 Twitter |

knowledgevis's Issues

It seems something wrong with online demo

Applied to local LLM like llama

Dear developer,

First of all, thank you for sharing your work. I would like to inquire whether KnowledgeVIS can load a local llama model. If so, what modifications are necessary?