Initial commit

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.spm filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,616 @@
+---
+library_name: transformers
+language:
+- de
+- en
+- es
+- fr
+- lt
+- lv
+- prg
+- pt
+- sgs
+
+tags:
+- translation
+- opus-mt-tc-bible
+
+license: apache-2.0
+model-index:
+- name: opus-mt-tc-bible-big-deu_eng_fra_por_spa-bat
+  results:
+  - task:
+      name: Translation deu-lit
+      type: translation
+      args: deu-lit
+    dataset:
+      name: flores200-devtest
+      type: flores200-devtest
+      args: deu-lit
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 22.6
+       - name: chr-F
+         type: chrf
+         value: 0.54957
+  - task:
+      name: Translation eng-lit
+      type: translation
+      args: eng-lit
+    dataset:
+      name: flores200-devtest
+      type: flores200-devtest
+      args: eng-lit
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 27.7
+       - name: chr-F
+         type: chrf
+         value: 0.59338
+  - task:
+      name: Translation fra-lit
+      type: translation
+      args: fra-lit
+    dataset:
+      name: flores200-devtest
+      type: flores200-devtest
+      args: fra-lit
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 22.3
+       - name: chr-F
+         type: chrf
+         value: 0.54683
+  - task:
+      name: Translation por-lit
+      type: translation
+      args: por-lit
+    dataset:
+      name: flores200-devtest
+      type: flores200-devtest
+      args: por-lit
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 22.6
+       - name: chr-F
+         type: chrf
+         value: 0.55033
+  - task:
+      name: Translation spa-lit
+      type: translation
+      args: spa-lit
+    dataset:
+      name: flores200-devtest
+      type: flores200-devtest
+      args: spa-lit
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 16.9
+       - name: chr-F
+         type: chrf
+         value: 0.50725
+  - task:
+      name: Translation deu-lav
+      type: translation
+      args: deu-lav
+    dataset:
+      name: flores101-devtest
+      type: flores_101
+      args: deu lav devtest
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 24.4
+       - name: chr-F
+         type: chrf
+         value: 0.54724
+  - task:
+      name: Translation eng-lav
+      type: translation
+      args: eng-lav
+    dataset:
+      name: flores101-devtest
+      type: flores_101
+      args: eng lav devtest
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 31.0
+       - name: chr-F
+         type: chrf
+         value: 0.59955
+  - task:
+      name: Translation eng-lit
+      type: translation
+      args: eng-lit
+    dataset:
+      name: flores101-devtest
+      type: flores_101
+      args: eng lit devtest
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 27.2
+       - name: chr-F
+         type: chrf
+         value: 0.58961
+  - task:
+      name: Translation fra-lav
+      type: translation
+      args: fra-lav
+    dataset:
+      name: flores101-devtest
+      type: flores_101
+      args: fra lav devtest
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 24.2
+       - name: chr-F
+         type: chrf
+         value: 0.54276
+  - task:
+      name: Translation fra-lit
+      type: translation
+      args: fra-lit
+    dataset:
+      name: flores101-devtest
+      type: flores_101
+      args: fra lit devtest
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 22.4
+       - name: chr-F
+         type: chrf
+         value: 0.54665
+  - task:
+      name: Translation spa-lav
+      type: translation
+      args: spa-lav
+    dataset:
+      name: flores101-devtest
+      type: flores_101
+      args: spa lav devtest
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 17.8
+       - name: chr-F
+         type: chrf
+         value: 0.50131
+  - task:
+      name: Translation deu-lav
+      type: translation
+      args: deu-lav
+    dataset:
+      name: ntrex128
+      type: ntrex128
+      args: deu-lav
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 16.8
+       - name: chr-F
+         type: chrf
+         value: 0.47980
+  - task:
+      name: Translation deu-lit
+      type: translation
+      args: deu-lit
+    dataset:
+      name: ntrex128
+      type: ntrex128
+      args: deu-lit
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 17.6
+       - name: chr-F
+         type: chrf
+         value: 0.50645
+  - task:
+      name: Translation eng-lav
+      type: translation
+      args: eng-lav
+    dataset:
+      name: ntrex128
+      type: ntrex128
+      args: eng-lav
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 20.6
+       - name: chr-F
+         type: chrf
+         value: 0.51026
+  - task:
+      name: Translation eng-lit
+      type: translation
+      args: eng-lit
+    dataset:
+      name: ntrex128
+      type: ntrex128
+      args: eng-lit
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 21.5
+       - name: chr-F
+         type: chrf
+         value: 0.54187
+  - task:
+      name: Translation fra-lav
+      type: translation
+      args: fra-lav
+    dataset:
+      name: ntrex128
+      type: ntrex128
+      args: fra-lav
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 15.5
+       - name: chr-F
+         type: chrf
+         value: 0.45346
+  - task:
+      name: Translation fra-lit
+      type: translation
+      args: fra-lit
+    dataset:
+      name: ntrex128
+      type: ntrex128
+      args: fra-lit
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 16.2
+       - name: chr-F
+         type: chrf
+         value: 0.48870
+  - task:
+      name: Translation por-lav
+      type: translation
+      args: por-lav
+    dataset:
+      name: ntrex128
+      type: ntrex128
+      args: por-lav
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 17.3
+       - name: chr-F
+         type: chrf
+         value: 0.47809
+  - task:
+      name: Translation por-lit
+      type: translation
+      args: por-lit
+    dataset:
+      name: ntrex128
+      type: ntrex128
+      args: por-lit
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 17.5
+       - name: chr-F
+         type: chrf
+         value: 0.50653
+  - task:
+      name: Translation spa-lav
+      type: translation
+      args: spa-lav
+    dataset:
+      name: ntrex128
+      type: ntrex128
+      args: spa-lav
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 17.1
+       - name: chr-F
+         type: chrf
+         value: 0.47690
+  - task:
+      name: Translation spa-lit
+      type: translation
+      args: spa-lit
+    dataset:
+      name: ntrex128
+      type: ntrex128
+      args: spa-lit
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 17.1
+       - name: chr-F
+         type: chrf
+         value: 0.50412
+  - task:
+      name: Translation deu-lit
+      type: translation
+      args: deu-lit
+    dataset:
+      name: tatoeba-test-v2021-08-07
+      type: tatoeba_mt
+      args: deu-lit
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 39.8
+       - name: chr-F
+         type: chrf
+         value: 0.65379
+  - task:
+      name: Translation eng-lav
+      type: translation
+      args: eng-lav
+    dataset:
+      name: tatoeba-test-v2021-08-07
+      type: tatoeba_mt
+      args: eng-lav
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 46.4
+       - name: chr-F
+         type: chrf
+         value: 0.68823
+  - task:
+      name: Translation eng-lit
+      type: translation
+      args: eng-lit
+    dataset:
+      name: tatoeba-test-v2021-08-07
+      type: tatoeba_mt
+      args: eng-lit
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 39.8
+       - name: chr-F
+         type: chrf
+         value: 0.67792
+  - task:
+      name: Translation multi-multi
+      type: translation
+      args: multi-multi
+    dataset:
+      name: tatoeba-test-v2020-07-28-v2023-09-26
+      type: tatoeba_mt
+      args: multi-multi
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 43.3
+       - name: chr-F
+         type: chrf
+         value: 0.68018
+  - task:
+      name: Translation spa-lit
+      type: translation
+      args: spa-lit
+    dataset:
+      name: tatoeba-test-v2021-08-07
+      type: tatoeba_mt
+      args: spa-lit
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 43.3
+       - name: chr-F
+         type: chrf
+         value: 0.68133
+  - task:
+      name: Translation eng-lav
+      type: translation
+      args: eng-lav
+    dataset:
+      name: newstest2017
+      type: wmt-2017-news
+      args: eng-lav
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 21.5
+       - name: chr-F
+         type: chrf
+         value: 0.53192
+  - task:
+      name: Translation eng-lit
+      type: translation
+      args: eng-lit
+    dataset:
+      name: newstest2019
+      type: wmt-2019-news
+      args: eng-lit
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 18.3
+       - name: chr-F
+         type: chrf
+         value: 0.51714
+---
+# opus-mt-tc-bible-big-deu_eng_fra_por_spa-bat
+
+## Table of Contents
+- [Model Details](#model-details)
+- [Uses](#uses)
+- [Risks, Limitations and Biases](#risks-limitations-and-biases)
+- [How to Get Started With the Model](#how-to-get-started-with-the-model)
+- [Training](#training)
+- [Evaluation](#evaluation)
+- [Citation Information](#citation-information)
+- [Acknowledgements](#acknowledgements)
+
+## Model Details
+
+Neural machine translation model for translating from unknown (deu+eng+fra+por+spa) to Baltic languages (bat).
+
+This model is part of the [OPUS-MT project](https://github.com/Helsinki-NLP/Opus-MT), an effort to make neural machine translation models widely available and accessible for many languages in the world. All models are originally trained using the amazing framework of [Marian NMT](https://marian-nmt.github.io/), an efficient NMT implementation written in pure C++. The models have been converted to pyTorch using the transformers library by huggingface. Training data is taken from [OPUS](https://opus.nlpl.eu/) and training pipelines use the procedures of [OPUS-MT-train](https://github.com/Helsinki-NLP/Opus-MT-train).
+**Model Description:**
+- **Developed by:** Language Technology Research Group at the University of Helsinki
+- **Model Type:** Translation (transformer-big)
+- **Release**: 2024-05-30
+- **License:** Apache-2.0
+- **Language(s):**  
+  - Source Language(s): deu eng fra por spa
+  - Target Language(s): lav lit prg sgs
+  - Valid Target Language Labels: >>lav<< >>lit<< >>ndf<< >>olt<< >>prg<< >>prg_Latn<< >>sgs<< >>svx<< >>sxl<< >>xcu<< >>xgl<< >>xsv<< >>xzm<<
+- **Original Model**: [opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-30.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/deu+eng+fra+por+spa-bat/opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-30.zip)
+- **Resources for more information:**
+  -  [OPUS-MT dashboard](https://opus.nlpl.eu/dashboard/index.php?pkg=opusmt&test=all&scoreslang=all&chart=standard&model=Tatoeba-MT-models/deu%2Beng%2Bfra%2Bpor%2Bspa-bat/opusTCv20230926max50%2Bbt%2Bjhubc_transformer-big_2024-05-30)
+  - [OPUS-MT-train GitHub Repo](https://github.com/Helsinki-NLP/OPUS-MT-train)
+  - [More information about MarianNMT models in the transformers library](https://huggingface.co/docs/transformers/model_doc/marian)
+  - [Tatoeba Translation Challenge](https://github.com/Helsinki-NLP/Tatoeba-Challenge/)
+  - [HPLT bilingual data v1 (as part of the Tatoeba Translation Challenge dataset)](https://hplt-project.org/datasets/v1)
+  - [A massively parallel Bible corpus](https://aclanthology.org/L14-1215/)
+
+This is a multilingual translation model with multiple target languages. A sentence initial language token is required in the form of `>>id<<` (id = valid target language ID), e.g. `>>lav<<`
+
+## Uses
+
+This model can be used for translation and text-to-text generation.
+
+## Risks, Limitations and Biases
+
+**CONTENT WARNING: Readers should be aware that the model is trained on various public data sets that may contain 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)](https://aclanthology.org/2021.acl-long.330.pdf) and [Bender et al. (2021)](https://dl.acm.org/doi/pdf/10.1145/3442188.3445922)).
+
+## How to Get Started With the Model
+
+A short example code:
+
+```python
+from transformers import MarianMTModel, MarianTokenizer
+
+src_text = [
+    ">>lav<< Replace this with text in an accepted source language.",
+    ">>sgs<< This is the second sentence."
+]
+
+model_name = "pytorch-models/opus-mt-tc-bible-big-deu_eng_fra_por_spa-bat"
+tokenizer = MarianTokenizer.from_pretrained(model_name)
+model = MarianMTModel.from_pretrained(model_name)
+translated = model.generate(**tokenizer(src_text, return_tensors="pt", padding=True))
+
+for t in translated:
+    print( tokenizer.decode(t, skip_special_tokens=True) )
+```
+
+You can also use OPUS-MT models with the transformers pipelines, for example:
+
+```python
+from transformers import pipeline
+pipe = pipeline("translation", model="Helsinki-NLP/opus-mt-tc-bible-big-deu_eng_fra_por_spa-bat")
+print(pipe(">>lav<< Replace this with text in an accepted source language."))
+```
+
+## Training
+
+- **Data**: opusTCv20230926max50+bt+jhubc ([source](https://github.com/Helsinki-NLP/Tatoeba-Challenge))
+- **Pre-processing**: SentencePiece (spm32k,spm32k)
+- **Model Type:**  transformer-big
+- **Original MarianNMT Model**: [opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-30.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/deu+eng+fra+por+spa-bat/opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-30.zip)
+- **Training Scripts**: [GitHub Repo](https://github.com/Helsinki-NLP/OPUS-MT-train)
+
+## Evaluation
+
+* [Model scores at the OPUS-MT dashboard](https://opus.nlpl.eu/dashboard/index.php?pkg=opusmt&test=all&scoreslang=all&chart=standard&model=Tatoeba-MT-models/deu%2Beng%2Bfra%2Bpor%2Bspa-bat/opusTCv20230926max50%2Bbt%2Bjhubc_transformer-big_2024-05-30)
+* test set translations: [opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-29.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/deu+eng+fra+por+spa-bat/opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-29.test.txt)
+* test set scores: [opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-29.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/deu+eng+fra+por+spa-bat/opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-29.eval.txt)
+* benchmark results: [benchmark_results.txt](benchmark_results.txt)
+* benchmark output: [benchmark_translations.zip](benchmark_translations.zip)
+
+| langpair | testset | chr-F | BLEU  | #sent | #words |
+|----------|---------|-------|-------|-------|--------|
+| deu-lit | tatoeba-test-v2021-08-07 | 0.65379 | 39.8 | 1115 | 7091 |
+| eng-lav | tatoeba-test-v2021-08-07 | 0.68823 | 46.4 | 1631 | 9932 |
+| eng-lit | tatoeba-test-v2021-08-07 | 0.67792 | 39.8 | 2528 | 14942 |
+| spa-lit | tatoeba-test-v2021-08-07 | 0.68133 | 43.3 | 454 | 2352 |
+| deu-lav | flores101-devtest | 0.54724 | 24.4 | 1012 | 22092 |
+| eng-lav | flores101-devtest | 0.59955 | 31.0 | 1012 | 22092 |
+| eng-lit | flores101-devtest | 0.58961 | 27.2 | 1012 | 20695 |
+| fra-lav | flores101-devtest | 0.54276 | 24.2 | 1012 | 22092 |
+| fra-lit | flores101-devtest | 0.54665 | 22.4 | 1012 | 20695 |
+| spa-lav | flores101-devtest | 0.50131 | 17.8 | 1012 | 22092 |
+| deu-lit | flores200-devtest | 0.54957 | 22.6 | 1012 | 20695 |
+| eng-lit | flores200-devtest | 0.59338 | 27.7 | 1012 | 20695 |
+| fra-lit | flores200-devtest | 0.54683 | 22.3 | 1012 | 20695 |
+| por-lit | flores200-devtest | 0.55033 | 22.6 | 1012 | 20695 |
+| spa-lit | flores200-devtest | 0.50725 | 16.9 | 1012 | 20695 |
+| eng-lav | newstest2017 | 0.53192 | 21.5 | 2001 | 39392 |
+| eng-lit | newstest2019 | 0.51714 | 18.3 | 998 | 19711 |
+| deu-lav | ntrex128 | 0.47980 | 16.8 | 1997 | 44709 |
+| deu-lit | ntrex128 | 0.50645 | 17.6 | 1997 | 41189 |
+| eng-lav | ntrex128 | 0.51026 | 20.6 | 1997 | 44709 |
+| eng-lit | ntrex128 | 0.54187 | 21.5 | 1997 | 41189 |
+| fra-lav | ntrex128 | 0.45346 | 15.5 | 1997 | 44709 |
+| fra-lit | ntrex128 | 0.48870 | 16.2 | 1997 | 41189 |
+| por-lav | ntrex128 | 0.47809 | 17.3 | 1997 | 44709 |
+| por-lit | ntrex128 | 0.50653 | 17.5 | 1997 | 41189 |
+| spa-lav | ntrex128 | 0.47690 | 17.1 | 1997 | 44709 |
+| spa-lit | ntrex128 | 0.50412 | 17.1 | 1997 | 41189 |
+
+## Citation Information
+
+* Publications: [Democratizing neural machine translation with OPUS-MT](https://doi.org/10.1007/s10579-023-09704-w) and [OPUS-MT – Building open translation services for the World](https://aclanthology.org/2020.eamt-1.61/) and [The Tatoeba Translation Challenge – Realistic Data Sets for Low Resource and Multilingual MT](https://aclanthology.org/2020.wmt-1.139/) (Please, cite if you use this model.)
+
+```bibtex
+@article{tiedemann2023democratizing,
+  title={Democratizing neural machine translation with {OPUS-MT}},
+  author={Tiedemann, J{\"o}rg and Aulamo, Mikko and Bakshandaeva, Daria and Boggia, Michele and Gr{\"o}nroos, Stig-Arne and Nieminen, Tommi and Raganato, Alessandro and Scherrer, Yves and Vazquez, Raul and Virpioja, Sami},
+  journal={Language Resources and Evaluation},
+  number={58},
+  pages={713--755},
+  year={2023},
+  publisher={Springer Nature},
+  issn={1574-0218},
+  doi={10.1007/s10579-023-09704-w}
+}
+
+@inproceedings{tiedemann-thottingal-2020-opus,
+    title = "{OPUS}-{MT} {--} Building open translation services for the World",
+    author = {Tiedemann, J{\"o}rg  and Thottingal, Santhosh},
+    booktitle = "Proceedings of the 22nd Annual Conference of the European Association for Machine Translation",
+    month = nov,
+    year = "2020",
+    address = "Lisboa, Portugal",
+    publisher = "European Association for Machine Translation",
+    url = "https://aclanthology.org/2020.eamt-1.61",
+    pages = "479--480",
+}
+
+@inproceedings{tiedemann-2020-tatoeba,
+    title = "The Tatoeba Translation Challenge {--} Realistic Data Sets for Low Resource and Multilingual {MT}",
+    author = {Tiedemann, J{\"o}rg},
+    booktitle = "Proceedings of the Fifth Conference on Machine Translation",
+    month = nov,
+    year = "2020",
+    address = "Online",
+    publisher = "Association for Computational Linguistics",
+    url = "https://aclanthology.org/2020.wmt-1.139",
+    pages = "1174--1182",
+}
+```
+
+## Acknowledgements
+
+The work is supported by the [HPLT project](https://hplt-project.org/), funded by the European Union’s Horizon Europe research and innovation programme under grant agreement No 101070350. We are also grateful for the generous computational resources and IT infrastructure provided by [CSC -- IT Center for Science](https://www.csc.fi/), Finland, and the [EuroHPC supercomputer LUMI](https://www.lumi-supercomputer.eu/).
+
+## Model conversion info
+
+* transformers version: 4.45.1
+* OPUS-MT git hash: 0882077
+* port time: Tue Oct  8 00:43:04 EEST 2024
+* port machine: LM0-400-22516.local

benchmark_results.txt

@@ -0,0 +1,32 @@
+multi-multi	tatoeba-test-v2020-07-28-v2023-09-26	0.68018	43.3	6367	38034
+deu-lav	flores101-devtest	0.54724	24.4	1012	22092
+eng-lav	flores101-devtest	0.59955	31.0	1012	22092
+eng-lit	flores101-devtest	0.58961	27.2	1012	20695
+fra-lav	flores101-devtest	0.54276	24.2	1012	22092
+fra-lit	flores101-devtest	0.54665	22.4	1012	20695
+spa-lav	flores101-devtest	0.50131	17.8	1012	22092
+deu-lit	flores200-devtest	0.54957	22.6	1012	20695
+eng-lit	flores200-devtest	0.59338	27.7	1012	20695
+fra-lit	flores200-devtest	0.54683	22.3	1012	20695
+por-lit	flores200-devtest	0.55033	22.6	1012	20695
+spa-lit	flores200-devtest	0.50725	16.9	1012	20695
+eng-lav	newstest2017	0.53192	21.5	2001	39392
+eng-lit	newstest2019	0.51714	18.3	998	19711
+deu-lav	ntrex128	0.47980	16.8	1997	44709
+deu-lit	ntrex128	0.50645	17.6	1997	41189
+eng-lav	ntrex128	0.51026	20.6	1997	44709
+eng-lit	ntrex128	0.54187	21.5	1997	41189
+fra-lav	ntrex128	0.45346	15.5	1997	44709
+fra-lit	ntrex128	0.48870	16.2	1997	41189
+por-lav	ntrex128	0.47809	17.3	1997	44709
+por-lit	ntrex128	0.50653	17.5	1997	41189
+spa-lav	ntrex128	0.47690	17.1	1997	44709
+spa-lit	ntrex128	0.50412	17.1	1997	41189
+eng-lit	tatoeba-test-v2020-07-28	0.67468	39.5	2500	14798
+spa-lit	tatoeba-test-v2020-07-28	0.68015	42.8	452	2341
+eng-lit	tatoeba-test-v2021-03-30	0.67451	39.5	5003	29598
+spa-lit	tatoeba-test-v2021-03-30	0.68064	42.8	457	2364
+deu-lit	tatoeba-test-v2021-08-07	0.65379	39.8	1115	7091
+eng-lav	tatoeba-test-v2021-08-07	0.68823	46.4	1631	9932
+eng-lit	tatoeba-test-v2021-08-07	0.67792	39.8	2528	14942
+spa-lit	tatoeba-test-v2021-08-07	0.68133	43.3	454	2352

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "pytorch-models/opus-mt-tc-bible-big-deu_eng_fra_por_spa-bat",
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "MarianMTModel"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 59472,
+  "decoder_vocab_size": 59473,
+  "dropout": 0.1,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 794,
+  "forced_eos_token_id": null,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "max_length": null,
+  "max_position_embeddings": 1024,
+  "model_type": "marian",
+  "normalize_embedding": false,
+  "num_beams": null,
+  "num_hidden_layers": 6,
+  "pad_token_id": 59472,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.1",
+  "use_cache": true,
+  "vocab_size": 59473
+}

generation_config.json

@@ -0,0 +1,16 @@
+{
+  "_from_model_config": true,
+  "bad_words_ids": [
+    [
+      59472
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 59472,
+  "eos_token_id": 794,
+  "forced_eos_token_id": 794,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 59472,
+  "transformers_version": "4.45.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:616de070605feaf979b012d637b0897383f39ea8eefd8decbd509f3fb417af56
+size 949298420

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66cf068395cce6051dc34937761735e3c6d4a5ad1812174d379af42d7e9f1b87
+size 949349701

source.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cea29a15c91ec7a8ea5ab10c658767ea741783eef15a4ea485c1e38906f49f00
+size 819310

special_tokens_map.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}

target.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cac0e1178e738a1ee0014be2dd4c93f0d79232e895ab2273cce38c61a9bf4b1c
+size 834052

tokenizer_config.json

@@ -0,0 +1 @@
+{"source_lang": "deu+eng+fra+por+spa", "target_lang": "bat", "unk_token": "<unk>", "eos_token": "</s>", "pad_token": "<pad>", "model_max_length": 512, "sp_model_kwargs": {}, "separate_vocabs": false, "special_tokens_map_file": null, "name_or_path": "marian-models/opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-30/deu+eng+fra+por+spa-bat", "tokenizer_class": "MarianTokenizer"}