# deepvk/USER2-base

This model is a Russian sentence encoder base model with 149 million parameters and long context support up to 8,192 tokens. It is fine tuned for retrieval and semantic tasks, and it uses task specific prefixes such as classification, clustering, search_query, and search_document.

## Cite this

- Page: https://huggingbay.xyz/artifact/hf-model-deepvk-user2-base
- Citation: deepvk/USER2-base. The Hugging Bay model record. https://huggingbay.xyz/artifact/hf-model-deepvk-user2-base (retrieved 2026-11-14).
- Check a downloaded file: run `shasum -a 256 <file>` (macOS), `sha256sum <file>` (Linux) or `Get-FileHash -Algorithm SHA256 <file>` (Windows), then compare with that file's SHA-256 at https://huggingbay.xyz/api/artifacts/hf-model-deepvk-user2-base/files?limit=100. How checks work: https://huggingbay.xyz/verification

## Facts

- Type: Embedding
- Task: sentence-similarity
- Framework: sentence-transformers
- License: apache-2.0: Permissive open license: commercial use, modification, and redistribution are permitted. (https://spdx.org/licenses/Apache-2.0.html)
- Source: https://huggingface.co/deepvk/USER2-base
- Hosting: hosted (15 files)
- Files: 15 hosted of 18 listed
- File counts: "listed" is every file in the source repository; only hosted files download from Hugging Bay, and the download plan lists the files it selects for one download, so its count can differ.
- Hosted here: 15 hosted of 18 listed
- Full repo upstream: 1.2 GB
- Recommended file: 596.1 MB · model.safetensors
- Download: https://huggingbay.xyz/api/artifacts/hf-model-deepvk-user2-base/download-plan (download plan: https://huggingbay.xyz/api/artifacts/hf-model-deepvk-user2-base/download-plan)
- Per-file SHA-256: available for 15 of 15 hosted files via https://huggingbay.xyz/api/artifacts/hf-model-deepvk-user2-base/files?limit=100
- Availability: Ready
- Downloadable: yes
- Run-ready: no (Hugging Bay has not certified a run path for this model; hosted bytes are downloadable and hash-checkable only)
- Peer-assisted fallbacks: 0 verified, 0 pending review
- Downloads: 8767
- Stars: 29
- Card completeness: 96%

## Description

This model is a Russian sentence encoder base model with 149 million parameters and long context support up to 8,192 tokens. It is fine tuned for retrieval and semantic tasks, and it uses task specific prefixes such as classification, clustering, search_query, and search_document.

## Model Card Facts

- Declared license: apache-2.0
- Pipeline: sentence-similarity
- Library: sentence-transformers
- Task categories: sentence-similarity
- Languages: ru
- Referenced datasets: deepvk/ru-HNP, deepvk/ru-WANLI, deepvk/cultura_ru_ed, Shitao/bge-m3-data, CarlBrendt/Summ_Dialog_News, IlyaGusev/gazeta, its5Q/habr_qna, wikimedia/wikipedia
- Paper ids: 2205.13147, 2401.00368
- File hints: 16 upstream file samples

## Referenced Data

- Dataset: deepvk/ru-HNP
- Dataset: deepvk/ru-WANLI
- Dataset: deepvk/cultura_ru_ed
- Dataset: Shitao/bge-m3-data
- Dataset: CarlBrendt/Summ_Dialog_News
- Dataset: IlyaGusev/gazeta
- Dataset: its5Q/habr_qna
- Dataset: wikimedia/wikipedia
- Dataset: RussianNLP/wikiomnia
- Paper: 2205.13147
- Paper: 2401.00368

## File Hints

- .gitattributes (1.5 KB)
- 1_Pooling/config.json (296 B)
- README.md (15 KB)
- assets/mrl.png (130 KB) LFS
- assets/training_stages.png (120 KB) LFS
- config.json (2.2 KB)
- config_sentence_transformers.json (359 B)
- model.safetensors (568 MB) LFS
- modules.json (229 B)
- onnx/config.json (2.2 KB)
- onnx/model.onnx (569 MB) LFS
- onnx/special_tokens_map.json (837 B)

## Quality Checklist

- Summary: passed
- Description: passed
- Model card metadata: passed
- License: passed
- Provenance: passed
- File inventory: passed
- Hosted bytes: passed
- Scan result: passed
- Manifest signature: passed

## Safety Notes

- External catalog metadata imported from Hugging Face public API on 2026-08-27T20:57:41.672Z.
- Open license detected as apache-2.0.
- Model card references dataset context: deepvk/ru-HNP, deepvk/ru-WANLI, deepvk/cultura_ru_ed, Shitao/bge-m3-data.
- Not a run kit: hosted, hash-checked bytes only; run readiness is not certified for this model yet.

## Actions

- Web: https://huggingbay.xyz/artifact/hf-model-deepvk-user2-base
- Files API: https://huggingbay.xyz/api/artifacts/hf-model-deepvk-user2-base/files?limit=100
- Metadata: https://huggingbay.xyz/api/artifacts/hf-model-deepvk-user2-base/metadata.json
- Distribution: https://huggingbay.xyz/api/artifacts/hf-model-deepvk-user2-base/distribution
- Manifest: https://huggingbay.xyz/api/manifests/hf-model-deepvk-user2-base
- Download plan (per-file SHA-256 + signed download URLs): https://huggingbay.xyz/api/artifacts/hf-model-deepvk-user2-base/download-plan
- Hosted download rows: https://huggingbay.xyz/api/downloadable-files?artifactId=hf-model-deepvk-user2-base&limit=100
- Request mirror: not applicable.
- Submit peer fallback for review: POST https://huggingbay.xyz/api/artifacts/hf-model-deepvk-user2-base/decentralized-fallbacks