SAVRN
Search Contact SAVRN

Open-weight model

parrot_paraphraser_on_T5

by Prithivi Da prithivida/parrot_paraphraser_on_T5

Parrot is a paraphrase based utterance augmentation framework purpose built to accelerate training NLU models. A paraphrase framework is more than just a paraphrasing model.

Parameters
Context
Weights891.7 MB
License
AccessOpen weights
Monthly Downloads1.4M

Model Card

Parrot is a paraphrase based utterance augmentation framework purpose built to accelerate training NLU models. A paraphrase framework is more than just a paraphrasing model. For more details on the library and usage please refer to the github page Huggingface lists 12 paraphrase models, RapidAPI lists 7 fremium and commercial paraphrasers like QuillBot, Rasa has discussed an experimental paraphraser for augmenting text data here, Sentence-transfomers offers a paraphrase mining utility and NLPAug offers word level augmentation with a PPDB (a multi-million paraphrase database). While these attempts at paraphrasing are great, there are still some gaps and paraphrasing is NOT yet a mainstream…

Excerpt from the card by Prithivi Da.

Configuration

Architecture
T5ForConditionalGeneration
Vocabulary size
32,128
Model type
t5

Identity and Version

Repository
prithivida/parrot_paraphraser_on_T5
Publisher
Prithivi Da
Task
Not stated by the source
Modality
Other
Library
transformers
Parameters
Not stated by the source
Languages
Not stated by the source
Revision
9f32aa1e456e8e8a90d97e8673365f3090fa49fa
First published
2022-03-02
Last updated
2021-05-18

Files and Weights

8 files, 892.5 MB in total. The weights are 2 files totalling 891.7 MB in bin.

Weights2 files · 891.7 MB
Configuration2 files · 3.2 KB
Tokenizer2 files · 793.5 KB
Documentation1 file · 6.4 KB
Repository1 file · 690 B
Every file
FileTypeSizeSHA-256
pytorch_model.binWeights891.7 MB f735ccab779f
training_args.binWeights2.4 KB ba69063ddf93
config.jsonConfiguration1.4 KB
special_tokens_map.jsonConfiguration1.8 KB
README.mdDocumentation6.4 KB
.gitattributesRepository690 B
spiece.modelTokenizer791.7 KB d60acb128cf7
tokenizer_config.jsonTokenizer1.9 KB

License and Download

License
Not stated by the source
Access
Open weights, no gate
Download size
891.7 MB
Download from Prithivi Da

Released by Prithivi Da through its official repository on Hugging Face.

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.