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.
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.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| pytorch_model.bin | Weights | 891.7 MB | f735ccab779f |
| training_args.bin | Weights | 2.4 KB | ba69063ddf93 |
| config.json | Configuration | 1.4 KB | — |
| special_tokens_map.json | Configuration | 1.8 KB | — |
| README.md | Documentation | 6.4 KB | — |
| .gitattributes | Repository | 690 B | — |
| spiece.model | Tokenizer | 791.7 KB | d60acb128cf7 |
| tokenizer_config.json | Tokenizer | 1.9 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 891.7 MB
Released by Prithivi Da through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 891.7 MB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.