Search and RAG

LaBSE для языков народов России (lingtrain)

A set of LaBSE fine-tunes that turn sentences into vectors: Buryat, Mari, Udmurt, Ingush, Chuvash, Sakha and Kalmyk. Trained on pairs with Russian; quality differs by language.

Developer
lingtrain, not disclosed
First release
Jul 2023
Latest release
Aug 2025
Sizes
LaBSE fine-tunes; parameter count is not stated on the cards
License
Commercial use with conditionsno license is stated on the model cards — check with the developer
Russian
Supported
Running
On your own serverAlso runs without a GPU
Industries
Documents and accounting, Education, Media and production, Science and research
Deploy on your server Hugging Face

What it does

  • Aligning parallel texts in Russian and a national language
  • Semantic search across bilingual archives
  • Building training sets for translation
  • Grouping similar texts

Where it is used

Education and cultureMedia and publishingResearch and language projects

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
fits
1 GPUOne GPU with 16–80 GB — mid-size versions
no versions
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. LaBSE для чувашского, три версии
  2. LaBSE для калмыцкого
  3. LaBSE для удмуртского
  4. LaBSE для ингушского
  5. LaBSE для марийского
  6. LaBSE для бурятского

How to run it

On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.Hugging Face
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems.

Frequently asked questions

Can LaBSE для языков народов России (lingtrain) be used in a commercial project?

With conditions. License: no license is stated on the model cards — check with the developer. Restrictions vary — region, company revenue, attribution requirements. Have a lawyer check the terms before a commercial launch.

What hardware does LaBSE для языков народов России (lingtrain) need?

At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller versions. Some versions also run on an ordinary CPU, without a GPU. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does LaBSE для языков народов России (lingtrain) support Russian?

Yes, Russian is listed on the model card.

Where can I download LaBSE для языков народов России (lingtrain) and what does it cost?

The LaBSE для языков народов России (lingtrain) weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.

How I deploy it for clients

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Similar models

Search and RAGBGE-M3BAAI · ChinaCommercial use allowed

A model for meaning-based search in about a hundred languages. The core of RAG: the bot finds the right part of a document before answering.

DetailsSearch and RAGE5 / multilingual-e5Microsoft · USACommercial use allowed

Proven models for semantic search. The multilingual versions work well with Russian and are still a reliable base for RAG.

DetailsTranslationSLONE: перевод для языков народов РоссииSLONE (David Dale, Aigiz Kunafin and others) · not disclosedCommercial use with conditions

A community that extends NLLB and mBART to low-resource languages. Its models cover Erzya, Tuvan, Bashkir, Tatar, Chuvash, Buryat, Mari, Khakas and Karachay-Balkar. Quality differs by language, so test it on your own texts.

Details

Source: huggingface.co/lingtrain/labse-chuvash. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.