这是 LaBSE 模型到 PyTorch 的移植版本。它可用于将 109 种语言映射到一个共享的向量空间。
当您安装了 sentence-transformers 后，使用此模型会变得非常简单：
pip install -U sentence-transformers然后您可以像这样使用该模型：
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('lvzhou/LaBSE')
embeddings = model.encode(sentences)
print(embeddings)openmind 使用方法
from openmind 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()
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('/home/ma-user/work/pretrainmodel/LaBSE')
model = AutoModel.from_pretrained('/home/ma-user/work/pretrainmodel/LaBSE')
sentences = ['如何更换花呗绑定银行卡', 'How to replace the Huabei bundled bank card']
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, 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'])
print("Sentence embeddings:")
print(sentence_embeddings)如需对该模型进行自动化评估，请参见句子嵌入基准测试：https://seb.sbert.net
SentenceTransformer(
(0): Transformer({'max_seq_length': 256, 'do_lower_case': False}) with Transformer model: BertModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
(2): Dense({'in_features': 768, 'out_features': 768, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
(3): Normalize()
)有关描述 LaBSE 的相应出版物，请查看 LaBSE。