This is a new version of the repository. Do let us know (lindat-help at ufal.mff.cuni.cz) if you encounter any issues.
 
Please use the following text to cite this item or export to a predefined format:
Hrabal, Miroslav; et al., 2025, EdUKate translation models 2025, LINDAT/CLARIAH-CZ digital library at the Institute of Formal and Applied Linguistics (ÚFAL), http://hdl.handle.net/11234/1-6032.
dc.contributor.authorHrabal, Miroslav
dc.contributor.authorPopel, Martin
dc.contributor.authorPoláková, Lucie
dc.contributor.authorNovák, Michal
dc.contributor.authorKloudová, Věra
dc.contributor.authorAnisimova, Mariia
dc.date.accessioned2025-11-12T10:23:44Z
dc.date.available2025-11-12T10:23:44Z
dc.date.issued2025
dc.descriptionThis package includes three models adapted for sentence-level machine translation in educational domain: Czech-to-Ukrainian, Czech-to-English and Czech-to-German. The models are provided as LoRA adapters on top of EuroLLM-9B-Instruct LLM and can be used in the Charles Translator service (https://translator.cuni.cz) and in the web portal Škola s nadhledem (https://skolasnadhledem.cz/). The models were developed within the EdUKate project, which aims to help mitigate language barriers between non-Czech-speaking children in the Czech Republic and the education in the Czech school system. The project focuses on the development and dissemination of multilingual digital learning materials for students in primary and secondary schools.
dc.identifier.urihttp://hdl.handle.net/11234/1-6032
dc.language.isoces
dc.language.isoukr
dc.language.isoeng
dc.language.isodeu
dc.publisherCharles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)
dc.relation.isreferencedbyhttps://aclanthology.org/2025.wmt-1.44.pdf
dc.rightsCreative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)
dc.rights.labelPUB
dc.rights.urihttp://creativecommons.org/licenses/by-nc-sa/4.0/
dc.source.urihttps://ufal.mff.cuni.cz/grants/edukate
dc.subjectmachine translation
dc.subjectLLM
dc.subjecteducation
dc.titleEdUKate translation models 2025
dc.typetoolService
local.contact.personMartin Popel popel@ufal.mff.cuni.cz Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)
local.demo.urihttps://translator.cuni.cz
local.files.count3
local.files.size1901424609
local.has.filesyes
local.language.nameCzech
local.language.nameUkrainian
local.language.nameEnglish
local.language.nameGerman
local.sponsornationalFunds TQ01000458 Technologická agentura ČR EdUKate: Podpora digitálního vzdělávání cizojazyčných dětí prostřednictvím počítačového překladu
metashare.ResourceInfo#ContentInfo.detailedTypetool
metashare.ResourceInfo#ResourceComponentType#ToolServiceInfo.languageDependenttrue
 Files in this item
Name
cs-en.zip
Size
722.5 MB
Format
application/zip
Description
Zip
MD5
7403373a6dc490b69224c1214a0db8bb
Preview
  File Preview
  • csen
    • tokenizer.model2 MB
    • tokenizer.json15 MB
    • special_tokens_map.json557 B
    • tokenizer_config.json45 kB
    • adapter_config.json945 B
    • generation_config.json163 B
    • adapter_model.safetensors777 MB
    • chat_template.jinja295 B
Name
cs-de.zip
Size
363.5 MB
Format
application/zip
Description
Zip
MD5
88583e490c1afb8ccc6c79afcf4455a1
Preview
  File Preview
  • csde
    • tokenizer.model2 MB
    • tokenizer.json15 MB
    • special_tokens_map.json557 B
    • tokenizer_config.json45 kB
    • adapter_config.json944 B
    • generation_config.json163 B
    • adapter_model.safetensors388 MB
    • chat_template.jinja295 B
Name
cs-uk.zip
Size
727.34 MB
Format
application/zip
Description
Zip
MD5
94d4f7dd447eb71ec7672e17fcd11baa
Preview
  File Preview
  • csuk
    • tokenizer.model2 MB
    • tokenizer.json15 MB
    • tokenizer_config.json45 kB
    • special_tokens_map.json557 B
    • adapter_config.json506 B
    • generation_config.json163 B
    • adapter_model.safetensors777 MB
    • chat_template.jinja295 B