Indo Sentence Bert Base

🚀 印尼句子BERT基础模型

这是一个 句子转换器 模型，它可以将句子和段落映射到768维的密集向量空间，可用于聚类或语义搜索等任务。

🚀 快速开始

✨ 主要特性

• 能够将句子和段落映射到768维的密集向量空间。
• 适用于聚类、语义搜索等任务。

📦 安装指南

如果你已经安装了 句子转换器，使用这个模型会非常简单：

pip install -U sentence-transformers

💻 使用示例

基础用法（使用句子转换器库）

from sentence_transformers import SentenceTransformer
sentences = ["Ibukota Perancis adalah Paris", 
            "Menara Eifel terletak di Paris, Perancis", 
            "Pizza adalah makanan khas Italia", 
            "Saya kuliah di Carneige Mellon University"]

model = SentenceTransformer('firqaaa/indo-sentence-bert-base')
embeddings = model.encode(sentences)
print(embeddings)

高级用法（使用HuggingFace Transformers库）

如果没有安装 句子转换器，你可以按以下方式使用该模型：首先，将输入数据通过转换器模型，然后对上下文词嵌入应用正确的池化操作。

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()
    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)


# Sentences we want sentence embeddings for
sentences = ["Ibukota Perancis adalah Paris", 
             "Menara Eifel terletak di Paris, Perancis", 
             "Pizza adalah makanan khas Italia", 
             "Saya kuliah di Carneige Mellon University"]


# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('firqaaa/indo-sentence-bert-base')
model = AutoModel.from_pretrained('firqaaa/indo-sentence-bert-base')

# 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)

📚 详细文档

评估结果

要对该模型进行自动评估，请参考 句子嵌入基准测试：https://seb.sbert.net

训练信息

该模型使用以下参数进行训练：

• 数据加载器： sentence_transformers.datasets.NoDuplicatesDataLoader.NoDuplicatesDataLoader，长度为19644，参数如下：

{'batch_size': 16}

• 损失函数： sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss，参数如下：

{'scale': 20.0, 'similarity_fct': 'cos_sim'}

• fit() 方法的参数：

{
    "epochs": 5,
    "evaluation_steps": 0,
    "evaluator": "NoneType",
    "max_grad_norm": 1,
    "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
    "optimizer_params": {
        "lr": 2e-05
    },
    "scheduler": "WarmupLinear",
    "steps_per_epoch": null,
    "warmup_steps": 9930,
    "weight_decay": 0.01
}

完整模型架构

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)

引用与作者

  @inproceedings{reimers-2019-sentence-bert,
  title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
  author = "Reimers, Nils and Gurevych, Iryna",
  booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
  month = "11",
  year = "2019",
  publisher = "Association for Computational Linguistics",
  url = "https://arxiv.org/abs/1908.10084",

@misc{author = {Arasyi, Firqa},
  title  = {indo-sentence-bert: Sentence Transformer for Bahasa Indonesia with Multiple Negative Ranking Loss},
  year = {2022},
  month = {9}
  publisher = {huggingface},
  journal = {huggingface repository},
  howpublished = {https://huggingface.co/firqaaa/indo-sentence-bert-base}
}

📄 许可证

本项目采用 Apache-2.0 许可证。