source languages: nl; target languages: en; OPUS readme: nl-en; dataset: opus; model: transformer-align; pre-processing: normalization + SentencePiece.
Open-weight model · Translation
opus-mt-ru-en
by Helsinki-NLP Research Group Helsinki-NLP/opus-mt-ru-en
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.
Parameters—
Context512
Weights1.2 GB
Licensecc-by-4.0
AccessOpen weights
Monthly Downloads380.8k
Model Card
By Helsinki-NLP Research Group, published under cc-by-4.0, revision fbd6dc73284f.
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: ru-en
Read Helsinki-NLP Research Group's full model card
Table of Contents
- Model Details
- Uses
- Risks, Limitations and Biases
- Training
- Evaluation
- Citation Information
- How to Get Started With the Model
Model Details
Model Description:
- Developed by: Language Technology Research Group at the University of Helsinki
- Model Type: Transformer-align
- Language(s):
- Source Language: Russian
- Target Language: English
- License: CC-BY-4.0
- Resources for more information:
- GitHub Repo
Uses
Direct Use
This model can be used for translation and text-to-text generation.
Risks, Limitations and Biases
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: ru-en
Training
Training Data
Preprocessing
- Pre-processing: Normalization + SentencePiece
- Dataset: opus
-
Download original weights: opus-2020-02-26.zip
-
Test set translations: opus-2020-02-26.test.txt
Evaluation
Results
- test set scores: opus-2020-02-26.eval.txt
Benchmarks
| testset | BLEU | chr-F |
|---|---|---|
| newstest2012.ru.en | 34.8 | 0.603 |
| newstest2013.ru.en | 27.9 | 0.545 |
| newstest2014-ruen.ru.en | 31.9 | 0.591 |
| newstest2015-enru.ru.en | 30.4 | 0.568 |
| newstest2016-enru.ru.en | 30.1 | 0.565 |
| newstest2017-enru.ru.en | 33.4 | 0.593 |
| newstest2018-enru.ru.en | 29.6 | 0.565 |
| newstest2019-ruen.ru.en | 31.4 | 0.576 |
| Tatoeba.ru.en | 61.1 | 0.736 |
Citation Information
@InProceedings{TiedemannThottingal:EAMT2020,
author = {J{\"o}rg Tiedemann and Santhosh Thottingal},
title = {{OPUS-MT} — {B}uilding open translation services for the {W}orld},
booktitle = {Proceedings of the 22nd Annual Conferenec of the European Association for Machine Translation (EAMT)},
year = {2020},
address = {Lisbon, Portugal}
}
How to Get Started With the Model
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
tokenizer = AutoTokenizer.from_pretrained("Helsinki-NLP/opus-mt-ru-en")
model = AutoModelForSeq2SeqLM.from_pretrained("Helsinki-NLP/opus-mt-ru-en")
Configuration
- Architecture
- MarianMTModel
- Context length (tokens)
- 512
- Layers
- 6
- Vocabulary size
- 62,518
- Model type
- marian
Identity and Version
- Repository
- Helsinki-NLP/opus-mt-ru-en
- Publisher
- Helsinki-NLP Research Group
- Task
- Translation
- Modality
- Text
- Library
- transformers
- Parameters
- Not stated by the source
- Languages
- tf, ru, en
- Revision
- fbd6dc73284f95536648512cc21d57f19191961a
- First published
- 2022-03-02
- Last updated
- 2023-08-16
Files and Weights
11 files, 1.2 GB in total. The weights are 3 files totalling 1.2 GB in bin, h5, ot.
Weights3 files · 1.2 GB
Configuration2 files · 1.7 KB
Tokenizer2 files · 2.6 MB
Documentation1 file · 3.2 KB
Other2 files · 1.9 MB
Repository1 file · 345 B
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| pytorch_model.bin | Weights | 307.0 MB | 535450eb5613 |
| rust_model.ot | Weights | 563.1 MB | 5e910b59f7b0 |
| tf_model.h5 | Weights | 307.5 MB | b3c90598b2fd |
| config.json | Configuration | 1.4 KB | — |
| generation_config.json | Configuration | 293 B | — |
| README.md | Documentation | 3.2 KB | — |
| source.spm | Other | 1.1 MB | — |
| target.spm | Other | 802.8 KB | — |
| .gitattributes | Repository | 345 B | — |
| tokenizer_config.json | Tokenizer | 42 B | — |
| vocab.json | Tokenizer | 2.6 MB | — |
License and Download
- License
- cc-by-4.0
- Access
- Open weights, no gate
- Download size
- 1.2 GB
Download from Helsinki-NLP Research Group
Released by Helsinki-NLP Research Group through its official repository on Hugging Face. Read the license.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 1.2 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About opus-mt-ru-en
Can I use opus-mt-ru-en commercially?
Yes. opus-mt-ru-en is released under Creative Commons Attribution 4.0. CC BY 4.0 permits sharing and adapting the work, including commercially, provided the creator is credited and changes are indicated.
What is opus-mt-ru-en's context length?
512 tokens, from the maximum position embeddings in its published configuration.
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.