Downloads · 30 days
8
1% of all-time downloads
t5-vae-wiki
flax-community/t5-vae-wiki
t5-vae-wiki is a machine learning model from flax-community. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.
All-time downloads
779
Public
Repo size
1.8 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.msgpack892 MB · 100%
At a glance
- Library
- transformers
- License
- apache-2.0
- Model type
- transformer_vae
- Access
- Public
- Created
- Mar 2, 2022
- Updated
- Jul 19, 2021
- SHA
- b21190b3
Spaces
Model card
From the Hugging Face model README
T5-VAE-Wiki (flax)
A Transformer-VAE made using flax.
It has been trained to interpolate on sentences form wikipedia.
Done as part of Huggingface community training (see forum post).
Builds on T5, using an autoencoder to convert it into an MMD-VAE (more info).
How to use from the 🤗/transformers library
Add model repo as a submodule:
git submodule add https://github.com/Fraser-Greenlee/t5-vae-flax.git t5_vae_flax
from transformers import AutoTokenizer
from t5_vae_flax.src.t5_vae import FlaxT5VaeForAutoencoding
tokenizer = AutoTokenizer.from_pretrained("t5-base")
model = FlaxT5VaeForAutoencoding.from_pretrained("flax-community/t5-vae-wiki")
Setup
Run setup_tpu_vm_venv.sh to setup a virtual enviroment on a TPU VM for training.
- Library
- transformers
- Type
- transformer_vae
- License
- apache-2.0
- Languages
- en
- Created
- Mar 2, 2022
- Updated
- Jul 19, 2021