# ai-forever/ru-en-RoSBERTa

Model from Hugging Face for feature extraction: ai-forever/ru-en-RoSBERTa · sentence transformers

## Facts

- Type: Embedding
- Task: feature-extraction
- Framework: sentence-transformers
- License: mit — Permissive open license: commercial use, modification, and redistribution are permitted. (https://spdx.org/licenses/MIT.html)
- Source: https://huggingface.co/ai-forever/ru-en-RoSBERTa
- Hosting: hosted (11 files)
- Files: 11 hosted of 12 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: 11 files, 1.63 GB
- Full repo upstream: 1.63 GB
- Recommended file: 1.61 GB · model.safetensors
- Download: https://huggingbay.xyz/artifact/hf-model-ai-forever-ru-en-rosberta/files (download plan: https://huggingbay.xyz/api/artifacts/hf-model-ai-forever-ru-en-rosberta/download-plan)
- Per-file SHA-256: available for 11 of 11 hosted files via https://huggingbay.xyz/api/artifacts/hf-model-ai-forever-ru-en-rosberta/files?limit=100
- 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: 122153
- Stars: 87
- Card completeness: 96%

## Description

External Hugging Face catalog record for ai-forever/ru-en-RoSBERTa. Task: feature extraction. Library: sentence transformers. Languages: ru, en. Base model: ai-forever/ruRoberta-large. Includes 12 model-card evaluation signals. Popularity signal at import: 165,547 downloads and 87 likes.

## Model Card Facts

- Declared license: mit
- Pipeline: feature-extraction
- Library: sentence-transformers
- Base model: ai-forever/ruRoberta-large
- Task categories: feature-extraction
- Languages: ru, en
- Paper ids: 2408.12503
- Model-index entries: ru-en-RoSBERTa
- Evaluation signals: 12 model-card eval results
- File hints: 12 upstream file samples

## Evaluation Signals

- MTEB CEDRClassification (default): accuracy = 44.68650371944739 (MultilabelClassification)
- MTEB CEDRClassification (default): f1 = 40.7601061886426 (MultilabelClassification)
- MTEB CEDRClassification (default): lrap = 70.69633368756747 (MultilabelClassification)
- MTEB CEDRClassification (default): main_score = 44.68650371944739 (MultilabelClassification)
- MTEB GeoreviewClassification (default): accuracy = 49.697265625 (Classification)
- MTEB GeoreviewClassification (default): f1 = 47.793186725286866 (Classification)
- MTEB GeoreviewClassification (default): f1_weighted = 47.79131720298068 (Classification)
- MTEB GeoreviewClassification (default): main_score = 49.697265625 (Classification)
- MTEB GeoreviewClusteringP2P (default): main_score = 65.42249614873316 (Clustering)
- MTEB GeoreviewClusteringP2P (default): v_measure = 65.42249614873316 (Clustering)

## Referenced Data

- Paper: 2408.12503

## File Hints

- .gitattributes (1.5 KB)
- 1_Pooling/config.json (297 B)
- README.md (51 KB)
- config.json (715 B)
- config_sentence_transformers.json (241 B)
- merges.txt (1.7 MB)
- model.safetensors (1.5 GB) LFS
- modules.json (349 B)
- special_tokens_map.json (958 B)
- tokenizer.json (5.7 MB)
- tokenizer_config.json (1.2 KB)
- vocab.json (2.4 MB)

## 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 2026-08-27T20:34:25.439Z.
- Open license detected as mit.
- Model-index metadata found for ru-en-RoSBERTa.
- 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-ai-forever-ru-en-rosberta
- Files API: https://huggingbay.xyz/api/artifacts/hf-model-ai-forever-ru-en-rosberta/files?limit=100
- Metadata: https://huggingbay.xyz/api/artifacts/hf-model-ai-forever-ru-en-rosberta/metadata.json
- Distribution: https://huggingbay.xyz/api/artifacts/hf-model-ai-forever-ru-en-rosberta/distribution
- Manifest: https://huggingbay.xyz/api/manifests/hf-model-ai-forever-ru-en-rosberta
- Download plan (per-file SHA-256 + signed download URLs): https://huggingbay.xyz/api/artifacts/hf-model-ai-forever-ru-en-rosberta/download-plan
- Hosted download rows: https://huggingbay.xyz/api/downloadable-files?artifactId=hf-model-ai-forever-ru-en-rosberta&limit=100
- Request mirror: not applicable.
- Submit peer fallback for review: POST https://huggingbay.xyz/api/artifacts/hf-model-ai-forever-ru-en-rosberta/decentralized-fallbacks