Home
Embeddings ⚡ NEW ⚡
A set of demos showcasing the flexibility and intricacy of GPT Embeddings using the text-embedding-ada-002 model.
A sample cl100k Tokenizer, of the type used to encode text prior to processing by GPT models. This implementation was built in a way that it makes it easier to understand what is happening during the tokenization process. As such, it is wildly inefficient and should not be considered for use in production. Please use SharpToken or TikTokenSharp for .NET production applications.
A demonstration of a variety of AI techniques used to create different strategies for playing a variant of the Chutes & Ladders board game.
A demonstration of an AI solution that is a Hybrid of Optimization and Logical techniques. This allows the AI to not only find the best possible solution, it can provide details as to why that solution was selected.
A demonstration of using an alternative optimization mechanism to train an ML model. In this case, we use the bio-inspired Amoeba Optimization method to train a model that predicts the political party of a congressperson based on his or her pattern of voting.