sbert_large_nlu_ru

64.1K

96

512

Small context

425M

1 language

license:mit

by

ai-forever

Embedding Model

OTHER

Fair

64K downloads

Community-tested

Try on Hugging Face Add to Compare

Edge AI:

Mobile

Laptop

Server

1GB+ RAM

Mobile

Laptop

Server

Quick Summary

BERT large model (uncased) for Sentence Embeddings in Russian language.

Device Compatibility

Mobile

4-6GB RAM

Laptop

16GB RAM

Server

GPU

Minimum Recommended

1GB+ RAM

Code Examples

Usage (HuggingFace Models Repository)pythontransformers

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/sbert_large_nlu_ru")
model = AutoModel.from_pretrained("ai-forever/sbert_large_nlu_ru")

#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'])

Usage (HuggingFace Models Repository)pythontransformers

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/sbert_large_nlu_ru")
model = AutoModel.from_pretrained("ai-forever/sbert_large_nlu_ru")

#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'])

Usage (HuggingFace Models Repository)pythontransformers

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/sbert_large_nlu_ru")
model = AutoModel.from_pretrained("ai-forever/sbert_large_nlu_ru")

#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'])

Usage (HuggingFace Models Repository)pythontransformers

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/sbert_large_nlu_ru")
model = AutoModel.from_pretrained("ai-forever/sbert_large_nlu_ru")

#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'])

Usage (HuggingFace Models Repository)pythontransformers

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/sbert_large_nlu_ru")
model = AutoModel.from_pretrained("ai-forever/sbert_large_nlu_ru")

#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'])

Usage (HuggingFace Models Repository)pythontransformers

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/sbert_large_nlu_ru")
model = AutoModel.from_pretrained("ai-forever/sbert_large_nlu_ru")

#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'])

Usage (HuggingFace Models Repository)pythontransformers

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/sbert_large_nlu_ru")
model = AutoModel.from_pretrained("ai-forever/sbert_large_nlu_ru")

#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'])

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

Production-ready inference API. Start free, scale to millions.

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.