Model reference · open weights

rubert-retriever

Available as managed deployment Embeddings sergeyzh · community Embeddings 1 variants 984 dl/mo

rubert-retriever is an open-weight embedding model from sergeyzh. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.

Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.

What it is

Released bysergeyzh
TypeEmbedding models
TaskEmbeddings
Parameters (lead)128M
Context512 tokens
Runs withsentence-transformers
Based onsergeyzh/BERTA
Released2026-04-14
Popularity984 downloads / month
LicenceOpen weights

About

What rubert-retriever is

Модель BERT для задач текстового поиска (retrieval). Модель получена дистилляцией эмбеддингов русских и английских текстов BAAI/bge-m3 в BERTA.

Основные характеристики модели:

  • размер ембеддинга - 768,
  • длина контекста - 512,
  • слоёв - 12,
  • префиксы - не требуются.
Read the full model card

Использование

from sentence_transformers import SentenceTransformer

model = SentenceTransformer('sergeyzh/rubert-base-retriever')

sentences = ["привет мир", "hello world", "здравствуй вселенная"]
embeddings = model.encode(sentences)
print(model.similarity(embeddings, embeddings))

Метрики

Оценки модели на задачах текстового поиска для русского языка:

Model NameMIRACL RerankingMIRACL RetrivalRiaNews RetrievalRuBQ RerankingRuBQ RetrievalAverage
bge-m30,6540,7020,8300,7400,7120,728
BERTA0,6430,6760,8160,7520,7100,719
rubert-base-retriever0,6350,6600,7870,7350,6990,703
multilingual-e5-base0,6050,6160,7020,7200,6960,668

Оценки модели на задачах текстового поиска для английского языка:

Model NameAILA StatutesArgu AnaLegal Bench Corporate LobbyingSCIDOCSStack Overflow QAStatcan Dialogue Dataset RetrievalWikipedia Retrieval MultilingualAverage
bge-m30,2980,5390,9040,1640,8060,2840,9240,560
rubert-base-retriever0,2490,5280,9120,1540,7030,3460,9280,546
multilingual-e5-large0,2080,5440,8970,1740,8890,1060,9110,533
multilingual-e5-base0,2040,4420,8900,1720,8510,1370,8880,512
BERTA0,1880,4140,9070,1120,4930,3040,8880,472

From the published model card. Full card on the HuggingFace links in the sidebar.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys rubert-retriever for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (rubert-retriever 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":"rubert-retriever","input":"text to embed"}'

Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.

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