metadata

license: mit
language:
  - ru
tags:
  - PyTorch
  - Transformers

ruELECTRA large model multitask (cased) for Embeddings in Russian language.

About model family https://arxiv.org/abs/2003.10555

Usage (HuggingFace Models Repository)

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

For better quality, use mean token 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-9)
    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("ai-forever/ruElectra-large")
model = AutoModel.from_pretrained("ai-forever/ruElectra-large")

#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;
Mark Baushenko: HF profile;
Artem Snegirev: HF profile