USER-bge-m3
Universal Sentence Encoder for Russian (USER) is a sentence-transformer model for extracting embeddings exclusively for Russian language. It maps sentences & paragraphs to a 1024 dimensional dense vector space and can be used for tasks like clustering or semantic search.
Params
360 M
Context
8,192
Downloads 30d
361 K
Likes
86
Download history
daily snapshots · 95 days
▲ 51 K in the last 30 days (12.4%)
412 K361 K
Oct 12Oct 22Nov 1Nov 10
438 K361 K
Aug 13Sep 12Oct 12Nov 10
438 K361 K
Aug 8Sep 8Oct 10Nov 10
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| model.safetensors | f32 | 1.4 GB | 2.1 GB | ✅ Runs comfortably |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Specifications
- Architecture
- XLMRobertaModel
- Parameters
- 360 M
- Tensor type
- F32
- Context length
- 8,192
- Vocabulary
- 46,166
- Layers / heads
- 24 / 16
- Licence
- apache-2.0
- First seen on the Hub
- 2024-07-05
- Training datasets
- deepvk/ru-HNP, deepvk/ru-WANLI, Shitao/bge-m3-data, RussianNLP/russian_super_glue, reciTAL/mlsum, Milana/russian_keywords, IlyaGusev/gazeta, d0rj/gsm8k-ru, bragovo/dsum_ru, CarlBrendt/Summ_Dialog_News
- Added to our catalog
- 2026-08-08
Compare with any sentence-similarity model