Dave Hillman
consultant ~ developer
Filling our lives with big things leaves less for the little things that may mean more.
Work smarter, not harder!
It's always darkest before it goes pitch black.
Located somewhere under the clear blue skys of North Carolina.
.jpeg)
Projects...
< Localized LLMs >
Localized Large Language Models (LLMs) are computational models that mimic how text is understood and used to simulate human intelligence.
Identify and evaluate LLMs for definitions, categorization, and summarization...running on localized CPU-based architectures.
ChatGPT and cloud-based LLMs are hardware resource intensive. Running LLMs on local machines means you're not subject to being connected all the time, have more privacy, and have the flexibility to change models as they improve.
Capabilities include categorization, document summarization, keyword extraction, definition generator, and question/response.
Latest efforts: trying to find a "sweet spot" commercial LLM that does most things, if not all, very well.
Technologies used
- LLMs
- Python
- LLM Support Libraries
- Web Stack
.jpeg)
.jpeg)
< Enhanced Entity Attribute Value (EEAV) >
EEAV is a very flexible model for capturing and exploiting data sets.
EEAV focuses on data-driven application development.
Starting with a table of data (CSV, JSON), ingest it, then manipulate it for a variety of pruposes. Any 2-dimensional data set can be captured in 3 tables: dataset, attributes, and values.
A secondary aspect of this effort is a web-based environment that makes it easily accessible and available.
Latest efforts: the REST interface is pretty much completed, documenting it all now.
Technologies used
- Python
- Web Stack
- Postgres, SQLite
- JavaScript, HTML, CSS
- Tabulator (table viewer)