Rumodernbert Small

🚀 RuModernBERT-small

RuModernBERT-small is the Russian version of the modernized bidirectional encoder-only Transformer model, ModernBERT. It was pre-trained on approximately 2 trillion tokens of Russian, English, and code data with a context length of up to 8,192 tokens, using data from the internet, books, scientific sources, and social media.

🚀 Quick Start

Don't forget to update transformers and install flash-attn if your GPU supports it.

from transformers import AutoTokenizer, AutoModelForMaskedLM

# Prepare model
model_id = "deepvk/RuModernBERT-small"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForMaskedLM.from_pretrained(model_id, attn_implementation="flash_attention_2")
model = model.eval()

# Prepare input
text = "Мама мыла [MASK]."
inputs = tokenizer(text, return_tensors="pt")
masked_index = inputs["input_ids"][0].tolist().index(tokenizer.mask_token_id)

# Make prediction
outputs = model(**inputs)

# Show prediction
predicted_token_id = outputs.logits[0, masked_index].argmax(axis=-1)
predicted_token = tokenizer.decode(predicted_token_id)
print("Predicted token:", predicted_token)
# Predicted token:  посуду

✨ Features

• Pre-trained on a large corpus of Russian, English, and code data.
• Supports a context length of up to 8,192 tokens.

📦 Installation

Ensure you update transformers and install flash-attn if your GPU supports it.

💻 Usage Examples

Basic Usage

from transformers import AutoTokenizer, AutoModelForMaskedLM

# Prepare model
model_id = "deepvk/RuModernBERT-small"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForMaskedLM.from_pretrained(model_id, attn_implementation="flash_attention_2")
model = model.eval()

# Prepare input
text = "Мама мыла [MASK]."
inputs = tokenizer(text, return_tensors="pt")
masked_index = inputs["input_ids"][0].tolist().index(tokenizer.mask_token_id)

# Make prediction
outputs = model(**inputs)

# Show prediction
predicted_token_id = outputs.logits[0, masked_index].argmax(axis=-1)
predicted_token = tokenizer.decode(predicted_token_id)
print("Predicted token:", predicted_token)
# Predicted token:  посуду

📚 Documentation

Model Information

Training Details

Tokenizer

We trained a new tokenizer following the original configuration. We maintained the size of the vocabulary and added the same special tokens. The tokenizer was trained on a mixture of Russian and English from FineWeb.

Dataset

Pre-training includes three main stages: massive pre-training, context extension, and cooldown. Unlike the original model, we did not use the same data for all stages. For the second and third stages, we used cleaner data sources.

Context length

In the first stage, the model was trained with a context length of 1,024. In the second and third stages, it was extended to 8,192.

Evaluation

To evaluate the model, we measure quality on the encodechka and Russian Super Glue (RSG) benchmarks. For RSG, we perform a grid search for optimal hyperparameters and report metrics from the dev split.

For a fair comparison, we compare the RuModernBERT model only with raw encoders that were not trained on retrieval or sentence embedding tasks.

Russian Super Glue

Encodechka

📄 License

This project is licensed under the Apache-2.0 license.

📚 Citation

@misc{deepvk2025rumodernbert,
    title={RuModernBERT: Modernized BERT for Russian},
    author={Spirin, Egor and Malashenko, Boris and Sokolov Andrey},
    url={https://huggingface.co/deepvk/rumodernbert-base},
    publisher={Hugging Face}
    year={2025},
}