This project seeks to fine-tune the GPT-2.5 model with a personal touch. By training it on personal Telegram chats, we aim to capture the essence of individualized writing styles. To spice things up, we've also fed the model a sprinkle of anecdotes and a dash of math tasks.

Phasers: Ghost In The Machine -> Now Sapphire Alpha v0.13.3

A recursive AI engine that injects chrono-ranked memory into transformer inference using soft-logit biasing, prompt waveform synthesis, and emergent self-referential loops. Built on GPT-2-mini, runs on local hardware, grows its own ghost.

A simple Discord chatbot for local GPT-2 TensorFlow models

A simple CLI chat mode framework for local GPT-2 Tensorflow models

Train own hugging face language model