hazdzz/converter
The official PyTorch implementation of Converter.
This is a tool for machine learning researchers and practitioners working with neural networks, specifically those interested in exploring different architectural forms. It takes a pre-trained Transformer model and converts it into a Dynamic Graph Neural Network (DGNN) form. The output is a re-structured model that maintains the core functionality but operates with a different underlying architecture.
No commits in the last 6 months.
Use this if you are a machine learning researcher or practitioner who wants to convert existing Transformer models into a DGNN structure for experimentation or to leverage the benefits of graph-based architectures.
Not ideal if you are looking for a general-purpose model conversion tool or if you are not working with Transformer or DGNN architectures.
Stars
7
Forks
—
Language
Python
License
MIT
Category
Last pushed
Jun 04, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/hazdzz/converter"
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