kyegomez/HeptapodLM

An Implementation of an Transformer model that generates tokens non-linearly all at once like the heptapods from Arrival

21
/ 100
Experimental

This project offers a novel way for researchers and deep learning practitioners to generate text not in a traditional line, but across a two-dimensional grid, much like a crossword puzzle or a complex diagram. It takes a matrix of tokens (like words or characters) as input and outputs a similarly structured matrix, where meaning is conveyed through spatial relationships. This is for those exploring experimental text generation beyond conventional sequential models, seeking to represent and create content with inherent multi-directional meaning.

No commits in the last 6 months.

Use this if you are a deep learning researcher or practitioner interested in exploring unconventional, non-linear text generation architectures inspired by the spatial arrangement of meaning.

Not ideal if you need a readily trainable model for established natural language processing tasks that require sequential text generation.

deep-learning-research experimental-nlp text-generation-architecture non-linear-modeling
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

10

Forks

Language

Python

License

MIT

Last pushed

Nov 11, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/kyegomez/HeptapodLM"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.