{
    "model_id": "DeepPavlov/rubert-base-cased",
    "downloads": 285331,
    "tags": [
        "transformers",
        "pytorch",
        "jax",
        "bert",
        "feature-extraction",
        "ru",
        "arxiv:1905.07213",
        "endpoints_compatible",
        "region:us"
    ],
    "description": "--- language: - ru --- # rubert-base-cased RuBERT \\(Russian, cased, 12‑layer, 768‑hidden, 12‑heads, 180M parameters\\) was trained on the Russian part of Wikipedia and news data. We used this training data to build a vocabulary of Russian subtokens and took a multilingual version of BERT‑base as an initialization for RuBERT\\[1\\]. 08.11.2021: upload model with MLM and NSP heads \\[1\\]: Kuratov, Y., Arkhipov, M. \\(2019\\). Adaptation of Deep Bidirectional Multilingual Transformers for Russian Language. arXiv preprint arXiv:1905.07213.",
    "model_explanation_gemini": "RuBERT is a Russian-language BERT model trained on Wikipedia and news data for masked language modeling and next sentence prediction tasks."
}