hunar4321/reweight-gpt

Reweight GPT - a simple neural network using transformer architecture for next character prediction

38
/ 100
Emerging

This project offers an alternative to the standard self-attention mechanism found in Transformer neural networks. It takes an input sequence of data, processes it using a direct re-weighting method, and produces predictions for the next element in the sequence. This is primarily useful for machine learning researchers and practitioners exploring new neural network architectures for sequence prediction tasks.

No commits in the last 6 months.

Use this if you are a machine learning researcher or engineer interested in experimenting with novel Transformer architectures for text or sequence generation.

Not ideal if you are looking for an out-of-the-box solution to train a language model or if you prefer standard, widely adopted Transformer implementations.

neural-networks transformer-architectures sequence-prediction deep-learning-research machine-learning-engineering
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

56

Forks

8

Language

Jupyter Notebook

License

MIT

Last pushed

Aug 28, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/hunar4321/reweight-gpt"

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