Model reference · open weights

ru-en-RoSBERTa

ru-en-RoSBERTa is an open-weight embedding model from ai-forever, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.

Embeddings ai-forever 1 variants 143k downloads/mo
Request this model on EU hardware All served models Not on the shared API today — deployed on request.

About

What ru-en-RoSBERTa is

Model Card for ru-en-RoSBERTa The ru-en-RoSBERTa is a general text embedding model for Russian. The model is based on ruRoBERTa and fine-tuned with ~4M pairs of supervised, synthetic and unsupervised data in Russian and English. Tokenizer supports some English tokens from RoBERTa tokenizer. For more model details please refer to our article. Usage The model can be used as is with prefixes. It is recommended to use CLS pooling. The choice of prefix and pooling depends on the task. We use the following basic rules to choose a prefix: - "searchquery: " and "searchdocument: " prefixes are for answer or relevant paragraph retrieval - "classification: " prefix is for symmetric paraphrasing related tasks (STS, NLI, Bitext Mining) - "clustering: " prefix is for any tasks that rely on thematic features (topic classification, title-body retrieval) To better tailor the model to your needs, you can fine-tune it with relevant high-quality Russian and English datasets. Below are examples of texts encoding using the Transformers and SentenceTransformers libraries. Transformers SentenceTransformers or using prompts (sentence-transformers=2.4.0): Citation Limitations The model is designed to process texts in Russian, the quality in English is unknown. Maximum input text length is limited to 512 tokens.

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

Makerai-forever
TypeEmbedding models
Parameters (lead)404M
Context514 tokens
Variants1
Runs withsentence-transformers
Based onai-forever/ruRoberta-large
Released2024-07-29
Popularity143k downloads / month
Likes89
LicenceOpen weights

How it works

How embedding models work

Your textsentence / documentEncodermaps meaningVectorlist of numbersAn embedding model turns text into a vector, so similar meanings sit close together — the basis of search and RAG.

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

VariantParamsPrecisionVRAMFits 16 GBWeights
ru-en-RoSBERTa404MBF16~0.9 GBWeights ↗

Benchmarks

Reported results

As published on the model card — the maker's own numbers, not measured by AxForge.

TaskDatasetMetricScore
MultilabelClassificationMTEB CEDRClassification (default)accuracy44.687
MultilabelClassificationMTEB CEDRClassification (default)f140.76
MultilabelClassificationMTEB CEDRClassification (default)lrap70.696
MultilabelClassificationMTEB CEDRClassification (default)main_score44.687
ClassificationMTEB GeoreviewClassification (default)accuracy49.697
ClassificationMTEB GeoreviewClassification (default)f147.793
ClassificationMTEB GeoreviewClassification (default)f1_weighted47.791
ClassificationMTEB GeoreviewClassification (default)main_score49.697
ClusteringMTEB GeoreviewClusteringP2P (default)main_score65.422
ClusteringMTEB GeoreviewClusteringP2P (default)v_measure65.422
ClusteringMTEB GeoreviewClusteringP2P (default)v_measure_std0.852
ClassificationMTEB HeadlineClassification (default)accuracy78.003
ClassificationMTEB HeadlineClassification (default)f177.952
ClassificationMTEB HeadlineClassification (default)f1_weighted77.951
ClassificationMTEB HeadlineClassification (default)main_score78.003
ClassificationMTEB InappropriatenessClassification (default)accuracy61.323
ClassificationMTEB InappropriatenessClassification (default)ap57.11
ClassificationMTEB InappropriatenessClassification (default)ap_weighted57.11
ClassificationMTEB InappropriatenessClassification (default)f160.971
ClassificationMTEB InappropriatenessClassification (default)f1_weighted60.971
ClassificationMTEB InappropriatenessClassification (default)main_score61.323
ClassificationMTEB KinopoiskClassification (default)accuracy63.273
ClassificationMTEB KinopoiskClassification (default)f161.007
ClassificationMTEB KinopoiskClassification (default)f1_weighted61.007

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys ru-en-rosberta for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (ru-en-rosberta below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/embeddings \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"ru-en-rosberta","input":"text to embed"}'

Details

Languages, data & research

Languages

ru en

Tags

sentence-transformers safetensors roberta feature-extraction mteb transformers ru en model-index text-embeddings-inference endpoints_compatible deploy:azure

Papers

Licence

Open weights

Open weights under mit — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗

Sources

Weights & code

Want ru-en-RoSBERTa on EU-owned hardware?

Request this model on EU hardware See what’s served now

Explore

More embedding models

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms