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 +1,475 @@
+---
+library_name: transformers
+language:
+- bru
+- cmo
+- de
+- en
+- es
+- fr
+- kha
+- km
+- kxm
+- mnw
+- ngt
+- pt
+- vi
+- wbm
+
+tags:
+- translation
+- opus-mt-tc-bible
+
+license: apache-2.0
+model-index:
+- name: opus-mt-tc-bible-big-deu_eng_fra_por_spa-mkh
+ results:
+ - task:
+ name: Translation deu-vie
+ type: translation
+ args: deu-vie
+ dataset:
+ name: flores200-devtest
+ type: flores200-devtest
+ args: deu-vie
+ metrics:
+ - name: BLEU
+ type: bleu
+ value: 33.9
+ - name: chr-F
+ type: chrf
+ value: 0.53535
+ - task:
+ name: Translation eng-vie
+ type: translation
+ args: eng-vie
+ dataset:
+ name: flores200-devtest
+ type: flores200-devtest
+ args: eng-vie
+ metrics:
+ - name: BLEU
+ type: bleu
+ value: 42.6
+ - name: chr-F
+ type: chrf
+ value: 0.60021
+ - task:
+ name: Translation fra-vie
+ type: translation
+ args: fra-vie
+ dataset:
+ name: flores200-devtest
+ type: flores200-devtest
+ args: fra-vie
+ metrics:
+ - name: BLEU
+ type: bleu
+ value: 34.6
+ - name: chr-F
+ type: chrf
+ value: 0.54168
+ - task:
+ name: Translation por-vie
+ type: translation
+ args: por-vie
+ dataset:
+ name: flores200-devtest
+ type: flores200-devtest
+ args: por-vie
+ metrics:
+ - name: BLEU
+ type: bleu
+ value: 35.9
+ - name: chr-F
+ type: chrf
+ value: 0.55046
+ - task:
+ name: Translation spa-vie
+ type: translation
+ args: spa-vie
+ dataset:
+ name: flores200-devtest
+ type: flores200-devtest
+ args: spa-vie
+ metrics:
+ - name: BLEU
+ type: bleu
+ value: 28.1
+ - name: chr-F
+ type: chrf
+ value: 0.50262
+ - task:
+ name: Translation deu-vie
+ type: translation
+ args: deu-vie
+ dataset:
+ name: flores101-devtest
+ type: flores_101
+ args: deu vie devtest
+ metrics:
+ - name: BLEU
+ type: bleu
+ value: 33.9
+ - name: chr-F
+ type: chrf
+ value: 0.53623
+ - task:
+ name: Translation eng-vie
+ type: translation
+ args: eng-vie
+ dataset:
+ name: flores101-devtest
+ type: flores_101
+ args: eng vie devtest
+ metrics:
+ - name: BLEU
+ type: bleu
+ value: 42.7
+ - name: chr-F
+ type: chrf
+ value: 0.59986
+ - task:
+ name: Translation por-vie
+ type: translation
+ args: por-vie
+ dataset:
+ name: flores101-devtest
+ type: flores_101
+ args: por vie devtest
+ metrics:
+ - name: BLEU
+ type: bleu
+ value: 35.7
+ - name: chr-F
+ type: chrf
+ value: 0.54819
+ - task:
+ name: Translation deu-vie
+ type: translation
+ args: deu-vie
+ dataset:
+ name: ntrex128
+ type: ntrex128
+ args: deu-vie
+ metrics:
+ - name: BLEU
+ type: bleu
+ value: 31.2
+ - name: chr-F
+ type: chrf
+ value: 0.51996
+ - task:
+ name: Translation eng-vie
+ type: translation
+ args: eng-vie
+ dataset:
+ name: ntrex128
+ type: ntrex128
+ args: eng-vie
+ metrics:
+ - name: BLEU
+ type: bleu
+ value: 42.7
+ - name: chr-F
+ type: chrf
+ value: 0.60050
+ - task:
+ name: Translation fra-vie
+ type: translation
+ args: fra-vie
+ dataset:
+ name: ntrex128
+ type: ntrex128
+ args: fra-vie
+ metrics:
+ - name: BLEU
+ type: bleu
+ value: 31.7
+ - name: chr-F
+ type: chrf
+ value: 0.51988
+ - task:
+ name: Translation por-vie
+ type: translation
+ args: por-vie
+ dataset:
+ name: ntrex128
+ type: ntrex128
+ args: por-vie
+ metrics:
+ - name: BLEU
+ type: bleu
+ value: 33.3
+ - name: chr-F
+ type: chrf
+ value: 0.52931
+ - task:
+ name: Translation spa-vie
+ type: translation
+ args: spa-vie
+ dataset:
+ name: ntrex128
+ type: ntrex128
+ args: spa-vie
+ metrics:
+ - name: BLEU
+ type: bleu
+ value: 33.1
+ - name: chr-F
+ type: chrf
+ value: 0.53347
+ - task:
+ name: Translation deu-vie
+ type: translation
+ args: deu-vie
+ dataset:
+ name: tatoeba-test-v2021-08-07
+ type: tatoeba_mt
+ args: deu-vie
+ metrics:
+ - name: BLEU
+ type: bleu
+ value: 25.3
+ - name: chr-F
+ type: chrf
+ value: 0.45222
+ - task:
+ name: Translation eng-vie
+ type: translation
+ args: eng-vie
+ dataset:
+ name: tatoeba-test-v2021-08-07
+ type: tatoeba_mt
+ args: eng-vie
+ metrics:
+ - name: BLEU
+ type: bleu
+ value: 39.0
+ - name: chr-F
+ type: chrf
+ value: 0.56413
+ - task:
+ name: Translation fra-vie
+ type: translation
+ args: fra-vie
+ dataset:
+ name: tatoeba-test-v2021-08-07
+ type: tatoeba_mt
+ args: fra-vie
+ metrics:
+ - name: BLEU
+ type: bleu
+ value: 35.6
+ - name: chr-F
+ type: chrf
+ value: 0.53078
+ - 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: 24.9
+ - name: chr-F
+ type: chrf
+ value: 0.43068
+ - task:
+ name: Translation spa-vie
+ type: translation
+ args: spa-vie
+ dataset:
+ name: tatoeba-test-v2021-08-07
+ type: tatoeba_mt
+ args: spa-vie
+ metrics:
+ - name: BLEU
+ type: bleu
+ value: 34.0
+ - name: chr-F
+ type: chrf
+ value: 0.51783
+---
+# opus-mt-tc-bible-big-deu_eng_fra_por_spa-mkh
+
+## 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 Mon-Khmer languages (mkh).
+
+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): bru cmo kha khm kxm mnw ngt vie wbm
+ - Valid Target Language Labels: >>aem<< >>alk<< >>aml<< >>bbh<< >>bdq<< >>bgk<< >>bgl<< >>blr<< >>brb<< >>bru<< >>brv<< >>btq<< >>caq<< >>cbn<< >>cma<< >>cmo<< >>cog<< >>crv<< >>crw<< >>cua<< >>cwg<< >>dnu<< >>hal<< >>hld<< >>hnu<< >>hre<< >>huo<< >>jah<< >>jeh<< >>jhi<< >>kdt<< >>kha<< >>khf<< >>khm<< >>kjg<< >>kjm<< >>knq<< >>kns<< >>kpm<< >>krr<< >>krv<< >>kta<< >>ktv<< >>kuf<< >>kxm<< >>kxy<< >>lbn<< >>lbo<< >>lcp<< >>lnh<< >>lwl<< >>lyg<< >>mef<< >>mhe<< >>mlf<< >>mml<< >>mng<< >>mnn<< >>mnq<< >>mnw<< >>moo<< >>mqt<< >>mra<< >>mtq<< >>mzt<< >>ncb<< >>ncq<< >>nev<< >>ngt<< >>ngt_Latn<< >>nik<< >>nuo<< >>nyl<< >>omx<< >>oog<< >>oyb<< >>pac<< >>pbv<< >>pcb<< >>pce<< >>phg<< >>pkt<< >>pll<< >>ply<< >>pnx<< >>prk<< >>prt<< >>puo<< >>rbb<< >>ren<< >>ril<< >>rka<< >>rmx<< >>sbo<< >>scb<< >>scq<< >>sct<< >>sea<< >>sed<< >>sii<< >>smu<< >>spu<< >>sqq<< >>ssm<< >>sss<< >>stg<< >>sti<< >>stt<< >>stu<< >>syo<< >>sza<< >>szc<< >>tdf<< >>tdr<< >>tea<< >>tef<< >>thm<< >>tkz<< >>tlq<< >>tmo<< >>tnz<< >>tou<< >>tpu<< >>tth<< >>tto<< >>tyh<< >>uuu<< >>vie<< >>vwa<< >>wbm<< >>xao<< >>xkk<< >>xnh<< >>xxx<< >>yin<< >>zng<<
+- **Original Model**: [opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-30.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/deu+eng+fra+por+spa-mkh/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-mkh/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. `>>bru<<`
+
+## 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 = [
+ ">>bru<< Replace this with text in an accepted source language.",
+ ">>wbm<< This is the second sentence."
+]
+
+model_name = "pytorch-models/opus-mt-tc-bible-big-deu_eng_fra_por_spa-mkh"
+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-mkh")
+print(pipe(">>bru<< 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-mkh/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-mkh/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-mkh/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-mkh/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-vie | tatoeba-test-v2021-08-07 | 0.45222 | 25.3 | 400 | 3768 |
+| eng-kha | tatoeba-test-v2021-08-07 | 9.076 | 0.4 | 1314 | 9269 |
+| eng-vie | tatoeba-test-v2021-08-07 | 0.56413 | 39.0 | 2500 | 24427 |
+| fra-vie | tatoeba-test-v2021-08-07 | 0.53078 | 35.6 | 1299 | 13219 |
+| spa-vie | tatoeba-test-v2021-08-07 | 0.51783 | 34.0 | 594 | 4740 |
+| deu-vie | flores101-devtest | 0.53623 | 33.9 | 1012 | 33331 |
+| eng-khm | flores101-devtest | 0.42022 | 1.4 | 1012 | 7006 |
+| eng-vie | flores101-devtest | 0.59986 | 42.7 | 1012 | 33331 |
+| por-vie | flores101-devtest | 0.54819 | 35.7 | 1012 | 33331 |
+| deu-vie | flores200-devtest | 0.53535 | 33.9 | 1012 | 33331 |
+| eng-khm | flores200-devtest | 0.41987 | 1.3 | 1012 | 7006 |
+| eng-vie | flores200-devtest | 0.60021 | 42.6 | 1012 | 33331 |
+| fra-khm | flores200-devtest | 0.40241 | 2.3 | 1012 | 7006 |
+| fra-vie | flores200-devtest | 0.54168 | 34.6 | 1012 | 33331 |
+| por-khm | flores200-devtest | 0.41582 | 2.3 | 1012 | 7006 |
+| por-vie | flores200-devtest | 0.55046 | 35.9 | 1012 | 33331 |
+| spa-vie | flores200-devtest | 0.50262 | 28.1 | 1012 | 33331 |
+| deu-khm | ntrex128 | 0.44917 | 3.2 | 1997 | 15866 |
+| deu-vie | ntrex128 | 0.51996 | 31.2 | 1997 | 64655 |
+| eng-khm | ntrex128 | 0.50215 | 1.6 | 1997 | 15866 |
+| eng-vie | ntrex128 | 0.60050 | 42.7 | 1997 | 64655 |
+| fra-khm | ntrex128 | 0.44024 | 2.3 | 1997 | 15866 |
+| fra-vie | ntrex128 | 0.51988 | 31.7 | 1997 | 64655 |
+| por-khm | ntrex128 | 0.46752 | 2.4 | 1997 | 15866 |
+| por-vie | ntrex128 | 0.52931 | 33.3 | 1997 | 64655 |
+| spa-khm | ntrex128 | 0.46166 | 2.5 | 1997 | 15866 |
+| spa-vie | ntrex128 | 0.53347 | 33.1 | 1997 | 64655 |
+| eng-khm | tico19-test | 0.54267 | 3.4 | 2100 | 15810 |
+| fra-khm | tico19-test | 0.45333 | 4.8 | 2100 | 15810 |
+| por-khm | tico19-test | 0.52339 | 6.8 | 2100 | 15810 |
+| spa-khm | tico19-test | 0.51848 | 6.8 | 2100 | 15810 |
+
+## 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 10:19:52 EEST 2024
+* port machine: LM0-400-22516.local

benchmark_results.txt

@@ -0,0 +1,45 @@
+multi-multi tatoeba-test-v2020-07-28-v2023-09-26 0.43068 24.9 8636 61987
+deu-khm flores101-devtest 0.38874 2.5 1012 7006
+deu-vie flores101-devtest 0.53623 33.9 1012 33331
+eng-khm flores101-devtest 0.42022 1.4 1012 7006
+eng-vie flores101-devtest 0.59986 42.7 1012 33331
+por-vie flores101-devtest 0.54819 35.7 1012 33331
+spa-khm flores101-devtest 0.37253 1.5 1012 7006
+deu-khm flores200-devtest 0.38872 2.5 1012 7006
+deu-vie flores200-devtest 0.53535 33.9 1012 33331
+eng-khm flores200-devtest 0.41987 1.3 1012 7006
+eng-vie flores200-devtest 0.60021 42.6 1012 33331
+fra-khm flores200-devtest 0.40241 2.3 1012 7006
+fra-vie flores200-devtest 0.54168 34.6 1012 33331
+por-khm flores200-devtest 0.41582 2.3 1012 7006
+por-vie flores200-devtest 0.55046 35.9 1012 33331
+spa-khm flores200-devtest 0.36975 1.5 1012 7006
+spa-vie flores200-devtest 0.50262 28.1 1012 33331
+eng-khm newstest2020 0.35200 0.9 2320 15454
+deu-khm ntrex128 0.44917 3.2 1997 15866
+deu-vie ntrex128 0.51996 31.2 1997 64655
+eng-khm ntrex128 0.50215 1.6 1997 15866
+eng-vie ntrex128 0.60050 42.7 1997 64655
+fra-khm ntrex128 0.44024 2.3 1997 15866
+fra-vie ntrex128 0.51988 31.7 1997 64655
+por-khm ntrex128 0.46752 2.4 1997 15866
+por-vie ntrex128 0.52931 33.3 1997 64655
+spa-khm ntrex128 0.46166 2.5 1997 15866
+spa-vie ntrex128 0.53347 33.1 1997 64655
+eng-khm tatoeba-test-v2020-07-28 0.33749 0.2 752 1737
+spa-khm tatoeba-test-v2020-07-28 0.36872 0.2 1472 3391
+deu-vie tatoeba-test-v2021-03-30 0.45438 25.3 401 3775
+eng-khm tatoeba-test-v2021-03-30 0.33751 0.2 754 1741
+spa-khm tatoeba-test-v2021-03-30 0.36872 0.2 1472 3391
+spa-vie tatoeba-test-v2021-03-30 0.51477 33.9 604 4824
+deu-vie tatoeba-test-v2021-08-07 0.45222 25.3 400 3768
+eng-kha tatoeba-test-v2021-08-07 9.076 0.4 1314 9269
+eng-khm tatoeba-test-v2021-08-07 0.33349 0.2 726 1692
+eng-vie tatoeba-test-v2021-08-07 0.56413 39.0 2500 24427
+fra-vie tatoeba-test-v2021-08-07 0.53078 35.6 1299 13219
+spa-khm tatoeba-test-v2021-08-07 0.36552 0.3 1448 3343
+spa-vie tatoeba-test-v2021-08-07 0.51783 34.0 594 4740
+eng-khm tico19-test 0.54267 3.4 2100 15810
+fra-khm tico19-test 0.45333 4.8 2100 15810
+por-khm tico19-test 0.52339 6.8 2100 15810
+spa-khm tico19-test 0.51848 6.8 2100 15810

config.json

@@ -0,0 +1,41 @@
+{
+ "_name_or_path": "pytorch-models/opus-mt-tc-bible-big-deu_eng_fra_por_spa-mkh",
+ "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": 57128,
+ "decoder_vocab_size": 57129,
+ "dropout": 0.1,
+ "encoder_attention_heads": 16,
+ "encoder_ffn_dim": 4096,
+ "encoder_layerdrop": 0.0,
+ "encoder_layers": 6,
+ "eos_token_id": 1104,
+ "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": 57128,
+ "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": 57129
+}

generation_config.json

@@ -0,0 +1,16 @@
+{
+ "_from_model_config": true,
+ "bad_words_ids": [
+ [
+ 57128
+ ]
+ ],
+ "bos_token_id": 0,
+ "decoder_start_token_id": 57128,
+ "eos_token_id": 1104,
+ "forced_eos_token_id": 1104,
+ "max_length": 512,
+ "num_beams": 4,
+ "pad_token_id": 57128,
+ "transformers_version": "4.45.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:beed128e73a7bf58d78092f4448fea328563d3f7f3a2bfafd356d0e9c1d67fa4
+size 939688020

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e4ba7532a6a1c9c479d9f2a792eb781294c7b7d22f05b44305fc1b9ac980b82
+size 939739269

source.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67336bd918550d52b7bd0940036ef81a5de8a57e47cb17a7ed616fa84e978628
+size 803212

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 sha256:67b72e3c21d85a89b92db1032a9a9f6c548dfaa976bf9ba2388085527b63dffa
+size 879868

tokenizer_config.json

@@ -0,0 +1 @@
+{"source_lang": "deu+eng+fra+por+spa", "target_lang": "mkh", "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-mkh", "tokenizer_class": "MarianTokenizer"}