Keytotext experimental package
Project description
keytotext
Idea is to build a model which will take keywords as inputs and generate sentences as outputs.
Model:
Two Models have been built:
- Using T5-base size = 850 MB can be found here: https://huggingface.co/gagan3012/keytotext
- Using T5-small size = 230 MB can be found here: https://huggingface.co/gagan3012/keytotext-small
- Updated model: https://huggingface.co/gagan3012/k2t
Usage:
from transformers import AutoTokenizer, AutoModelWithLMHead
tokenizer = AutoTokenizer.from_pretrained("gagan3012/k2t")
model = AutoModelWithLMHead.from_pretrained("gagan3012/k2t")
This uses a custom streamlit component built by me: GitHub
pip install streamlit-tags
The installation can also be found on PyPi
Example:
['India', 'Wedding'] -> We are celebrating today in New Delhi with three wedding anniversary parties.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
keytotext-0.1.0.tar.gz
(8.4 MB
view hashes)
Built Distribution
Close
Hashes for keytotext-0.1.0-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 38035257b5702a4bfa748eb2a367a318c1d96df6fd8fa0b4699e65055add81b7 |
|
MD5 | 40eb954075aa618ff2a94e73b7e58d4f |
|
BLAKE2b-256 | f4afcc513a83bcec7ab10b6ba05317884b5b252e64edaf802671bc5b6a4dfc14 |