templetwo/PhaseGPT
Kuramoto Phase-Coupled Oscillator Attention in Transformers
PhaseGPT helps conversational AI systems provide more useful and intentional responses. Instead of vaguely refusing or hallucinating, it enables models to classify questions into categories like 'harmful' or 'unknowable' and respond with specific tokens, followed by either a direct answer or a thoughtful exploration. This is for anyone who uses or develops AI chatbots and wants them to interact with users more intelligently and reliably, particularly when facing difficult or ambiguous questions.
Use this if you want your AI chatbot to understand the nature of a question (e.g., a factual query, a request for creative writing, or a harmful prompt) and respond appropriately, rather than giving generic answers or unintended refusals.
Not ideal if you need a simple, single-purpose chatbot that only answers factual questions or only generates creative text without needing to discern the intent or epistemic category of user input.
Stars
9
Forks
1
Language
Python
License
—
Category
Last pushed
Jan 10, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/templetwo/PhaseGPT"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
lucidrains/x-transformers
A concise but complete full-attention transformer with a set of promising experimental features...
kanishkamisra/minicons
Utility for behavioral and representational analyses of Language Models
lucidrains/simple-hierarchical-transformer
Experiments around a simple idea for inducing multiple hierarchical predictive model within a GPT
lucidrains/dreamer4
Implementation of Danijar's latest iteration for his Dreamer line of work
Nicolepcx/Transformers-in-Action
This is the corresponding code for the book Transformers in Action