ruElectra-small

RU-ELECTRA small model for Embeddings in Russian language.

The model architecture design, pretraining, and evaluation are documented in our preprint: A Family of Pretrained Transformer Language Models for Russian.

For better quality, use mean token embeddings.

Usage (HuggingFace Models Repository)

You can use the model directly from the model repository to compute sentence embeddings:

from transformers import AutoTokenizer, AutoModel
import torch
#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
    token_embeddings = model_output[0] #First element of model_output contains all token embeddings
    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
    sum_embeddings = torch.sum(token_embeddings * input_mask_expanded, 1)
    sum_mask = torch.clamp(input_mask_expanded.sum(1), min=1e-10)
    return sum_embeddings / sum_mask
#Sentences we want sentence embeddings for
sentences = ['Привет! Как твои дела?',
             'А правда, что 42 твое любимое число?']
#Load AutoModel from huggingface model repository
tokenizer = AutoTokenizer.from_pretrained("sberbank-ai/ruElectra-small")
model = AutoModel.from_pretrained("sberbank-ai/ruElectra-small")
#Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, max_length=24, return_tensors='pt')
#Compute token embeddings
with torch.no_grad():
    model_output = model(**encoded_input)
#Perform pooling. In this case, mean pooling
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])

Authors

• SaluteDevices RnD Team.

• Aleksandr Abramov: HF profile, Github, Kaggle Competitions Master;

• Cite us

@misc{zmitrovich2023family,
      title={A Family of Pretrained Transformer Language Models for Russian}, 
      author={Dmitry Zmitrovich and Alexander Abramov and Andrey Kalmykov and Maria Tikhonova and Ekaterina Taktasheva and Danil Astafurov and Mark Baushenko and Artem Snegirev and Tatiana Shavrina and Sergey Markov and Vladislav Mikhailov and Alena Fenogenova},
      year={2023},
      eprint={2309.10931},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}