seongminp/transformers-into-vaes

Code for "Finetuning Pretrained Transformers into Variational Autoencoders"

32
/ 100
Emerging

This project helps researchers and practitioners in natural language processing (NLP) adapt large, pre-trained language models for tasks requiring text generation and latent space manipulation. It takes an existing Transformer model and text datasets, and outputs a fine-tuned Variational Autoencoder (VAE) capable of generating diverse and coherent text. This is designed for NLP researchers and machine learning engineers working on advanced text generation and understanding.

No commits in the last 6 months.

Use this if you need to transform a pre-trained Transformer model into a Variational Autoencoder for tasks like controlled text generation or learning meaningful latent representations of text.

Not ideal if you are looking for a simple, off-the-shelf text generation tool without delving into model architecture fine-tuning.

natural-language-processing text-generation language-model-finetuning deep-learning-research
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 17 / 25

How are scores calculated?

Stars

40

Forks

11

Language

Python

License

Last pushed

May 26, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/seongminp/transformers-into-vaes"

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