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 openmind import AutoTokenizer, AutoModel, is_torch_npu_available
from openmind_hub import snapshot_download
import torch
import argparse
import torch.nn.functional as F
# 均值池化 - 考虑注意力掩码以进行正确的平均
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output[0] # model_output的第一个元素包含所有token嵌入
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)
def parse_args():
parser = argparse.ArgumentParser()
parser.add_argument(
"--model_name_or_path",
type=str,
help="Path to model",
default="zhouhui/LaBSE",
)
args = parser.parse_args()
return args
def main():
args = parse_args()
model_path = args.model_name_or_path
if is_torch_npu_available():
device = "npu:0"
else:
device = "cpu"
# 我们想要获取句子嵌入的句子
sentences = ['This is an example sentence', 'Each sentence is converted']
# 从openmind_hub加载模型
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModel.from_pretrained(model_path)
# 对句子进行分词
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
# 计算token嵌入
with torch.no_grad():
model_output = model(**encoded_input)
# 执行池化
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
# 归一化嵌入
sentence_embeddings = F.normalize(sentence_embeddings, p=2, dim=1)
print("Sentence embeddings:")
print(sentence_embeddings)
if __name__ == "__main__":
main()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 的相关出版物，请查看 LaBSE。