SAVRN
Search Contact SAVRN

Open-weight model

t5-base-grammar-correction

by Vennify AI vennify/t5-base-grammar-correction

This model generates a revised version of inputted text with the goal of containing fewer grammatical errors. It was trained with Happy Transformer using a dataset called JFLEG. Here's a full article on how to train a similar model.

Parameters
Context
Weights891.7 MB
Licensecc-by-nc-sa-4.0
AccessOpen weights
Monthly Downloads114.3k

Model Card

This model generates a revised version of inputted text with the goal of containing fewer grammatical errors. It was trained with Happy Transformer using a dataset called JFLEG. Here's a full article on how to train a similar model. pip install happytransformer

Excerpt from the card by Vennify AI, licensed cc-by-nc-sa-4.0.

Configuration

Architecture
T5ForConditionalGeneration
Vocabulary size
32,128
Stored precision
float32
Model type
t5

Identity and Version

Repository
vennify/t5-base-grammar-correction
Publisher
Vennify AI
Task
Not stated by the source
Modality
Other
Library
transformers
Parameters
Not stated by the source
Languages
en
Revision
9e4a09d21dca1072a69302df9261289d03c3ed78
First published
2022-03-02
Last updated
2022-01-14

Files and Weights

8 files, 893.9 MB in total. The weights are 1 file totalling 891.7 MB in bin.

Weights1 file · 891.7 MB
Configuration2 files · 3.2 KB
Tokenizer3 files · 2.2 MB
Documentation1 file · 939 B
Repository1 file · 737 B
Every file
FileTypeSizeSHA-256
pytorch_model.binWeights891.7 MB 10deee9a53b5
config.jsonConfiguration1.4 KB
special_tokens_map.jsonConfiguration1.8 KB
README.mdDocumentation939 B
.gitattributesRepository737 B
spiece.modelTokenizer791.7 KB d60acb128cf7
tokenizer.jsonTokenizer1.4 MB
tokenizer_config.jsonTokenizer1.9 KB

License and Download

License
cc-by-nc-sa-4.0
Access
Open weights, no gate
Download size
891.7 MB
Download from Vennify AI

Released by Vennify AI through its official repository on Hugging Face.

Built From

  • Described by arXiv:1702.04066
  • Trained on (disclosed) jfleg

Memory Requirements

PrecisionWeights in memory
As published891.7 MB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Questions About t5-base-grammar-correction

Can I use t5-base-grammar-correction commercially?

Not without separate permission. t5-base-grammar-correction is released under Creative Commons Attribution-NonCommercial-ShareAlike 4.0. CC BY-NC-SA 4.0 permits non-commercial sharing and adapting with credit, and requires adaptations to use the same license. Commercial use needs separate permission.