source languages: nl; target languages: en; OPUS readme: nl-en; dataset: opus; model: transformer-align; pre-processing: normalization + SentencePiece.
T5 is an encoder-decoder model pre-trained on a multi-task mixture of unsupervised and supervised tasks and for which each task is converted into a text-to-text format. For more information, please take a look at the original paper.
Parameters—
Context—
Weights593.3 MB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads8.6k
Model Card
By Ella Charlaix, published under apache-2.0, revision 47ee35f4310c.
T5 is an encoder-decoder model pre-trained on a multi-task mixture of unsupervised and supervised tasks and for which each task is converted into a text-to-text format. For more information, please take a look at the original paper. Paper: Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer Authors: Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, Peter J. Liu You can use this model with Transformers pipeline.
Read Ella Charlaix's full model card
t5-small exported to the OpenVINO IR.
Model description
T5 is an encoder-decoder model pre-trained on a multi-task mixture of unsupervised and supervised tasks and for which each task is converted into a text-to-text format.
For more information, please take a look at the original paper.
Paper: Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
Authors: Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, Peter J. Liu
Usage example
You can use this model with Transformers pipeline.
from transformers import AutoTokenizer, pipeline
from optimum.intel.openvino import OVModelForSeq2SeqLM
model_id = "echarlaix/t5-small-openvino"
model = OVModelForSeq2SeqLM.from_pretrained(model_id, use_cache=False)
tokenizer = AutoTokenizer.from_pretrained(model_id)
# Create a pipeline
translation_pipe = pipeline("translation_en_to_fr", model=model, tokenizer=tokenizer)
text = "He never went out without a book under his arm, and he often came back with two."
result = translation_pipe(text)
Configuration
- Architecture
- T5ForConditionalGeneration
- Vocabulary size
- 32,128
- Model type
- t5
Identity and Version
- Repository
- echarlaix/t5-small-openvino
- Publisher
- Ella Charlaix
- Task
- Translation
- Modality
- Text
- Library
- transformers
- Parameters
- Not stated by the source
- Languages
- en, fr, ro, de
- Revision
- 47ee35f4310c776e663da322860398ae63305179
- First published
- 2022-08-29
- Last updated
- 2023-01-03
Files and Weights
13 files, 598.3 MB in total. The weights are 3 files totalling 593.3 MB in bin.
Weights3 files · 593.3 MB
Configuration2 files · 3.6 KB
Tokenizer3 files · 3.2 MB
Documentation1 file · 1.4 KB
Other3 files · 1.7 MB
Repository1 file · 1.3 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| openvino_decoder_model.bin | Weights | 232.3 MB | 79fd697d099f |
| openvino_decoder_with_past_model.bin | Weights | 219.7 MB | 646f2a90d0e0 |
| openvino_encoder_model.bin | Weights | 141.3 MB | 60e2a56a5140 |
| config.json | Configuration | 1.4 KB | — |
| special_tokens_map.json | Configuration | 2.2 KB | — |
| README.md | Documentation | 1.4 KB | — |
| openvino_decoder_model.xml | Other | 687.7 KB | — |
| openvino_decoder_with_past_model.xml | Other | 640.7 KB | — |
| openvino_encoder_model.xml | Other | 359.7 KB | — |
| .gitattributes | Repository | 1.3 KB | — |
| spiece.model | Tokenizer | 791.7 KB | d60acb128cf7 |
| tokenizer.json | Tokenizer | 2.4 MB | — |
| tokenizer_config.json | Tokenizer | 2.3 KB | — |
License and Download
- License
- apache-2.0
- Access
- Open weights, no gate
- Download size
- 593.3 MB
Download from Ella Charlaix
Released by Ella Charlaix through its official repository on Hugging Face. Read the license.
Built From
- Described by arXiv:1910.10683
- Trained on (disclosed) c4
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 593.3 MB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About t5-small-openvino
Can I use t5-small-openvino commercially?
Yes. t5-small-openvino is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.
Similar Models
This is the model card of NLLB-200's distilled 600M variant. Here are the metrics for that particular checkpoint. - Information about training algorithms, parameters, fairness constraints or other applied approaches, and features. The exact training algorithm, data and the strategies to handle data imbalances for high and low resource languages that were used to train NLLB-200 is described in the paper. - Paper or other resource for more information NLLB Team et al, No Language Left Behind: Scaling Human-Centered Machine Translation, Arxiv, 2022 - Where to send questions or comments about the model: https://github.com/facebookresearch/fairseq/issues • Model performance measures: NLLB-200…
source languages: en; target languages: ru; OPUS readme: en-ru; dataset: opus; model: transformer-align; pre-processing: normalization + SentencePiece.
This model can be used for translation and text-to-text generation. CONTENT WARNING: Readers should be aware this section contains content that is disturbing, offensive, and can propagate historical and current stereotypes. Significant research has explored bias and fairness issues with language models (see, e.g., Sheng et al. (2021) and Bender et al. (2021)). Further details about the dataset for this model can be found in the OPUS readme: en-de
hfname: kor-eng - sourcelanguages: kor - targetlanguages: eng - opusreadmeurl: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/kor-eng/README.md - originalrepo: Tatoeba-Challenge - srcconstituents: {'korHani', 'korHang', 'korLatn', 'kor'} - tgtconstituents: {'eng'} - srcmultilingual: False - tgtmultilingual: False - urlmodel: https://object.pouta.csc.fi/Tatoeba-MT-models/kor-eng/opus-2020-06-17.zip - urltestset: https://object.pouta.csc.fi/Tatoeba-MT-models/kor-eng/opus-2020-06-17.test.txt - srcalpha3: kor - tgtalpha3: eng - shortpair: ko-en - chrF2score: 0.588 - brevitypenalty: 0.9590000000000001 - reflen: 17711.0 - srcname: Korean - tgtname: English - traindate…
source languages: de; target languages: en; OPUS readme: de-en; dataset: opus; model: transformer-align; pre-processing: normalization + SentencePiece.