🚀 印尼句子BERT基礎模型
這是一個 句子轉換器 模型,它可以將句子和段落映射到768維的密集向量空間,可用於聚類或語義搜索等任務。
🚀 快速開始
✨ 主要特性
- 能夠將句子和段落映射到768維的密集向量空間。
- 適用於聚類、語義搜索等任務。
📦 安裝指南
如果你已經安裝了 句子轉換器,使用這個模型會非常簡單:
pip install -U sentence-transformers
💻 使用示例
基礎用法(使用句子轉換器庫)
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)
高級用法(使用HuggingFace Transformers庫)
如果沒有安裝 句子轉換器,你可以按以下方式使用該模型:首先,將輸入數據通過轉換器模型,然後對上下文詞嵌入應用正確的池化操作。
from transformers import AutoTokenizer, AutoModel
import torch
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output[0]
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 = ["Ibukota Perancis adalah Paris",
"Menara Eifel terletak di Paris, Perancis",
"Pizza adalah makanan khas Italia",
"Saya kuliah di Carneige Mellon University"]
tokenizer = AutoTokenizer.from_pretrained('firqaaa/indo-sentence-bert-base')
model = AutoModel.from_pretrained('firqaaa/indo-sentence-bert-base')
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
with torch.no_grad():
model_output = model(**encoded_input)
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
print("Sentence embeddings:")
print(sentence_embeddings)
📚 詳細文檔
評估結果
要對該模型進行自動評估,請參考 句子嵌入基準測試:https://seb.sbert.net
訓練信息
該模型使用以下參數進行訓練:
- 數據加載器:
sentence_transformers.datasets.NoDuplicatesDataLoader.NoDuplicatesDataLoader
,長度為19644,參數如下:
{'batch_size': 16}
- 損失函數:
sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss
,參數如下:
{'scale': 20.0, 'similarity_fct': 'cos_sim'}
{
"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
}
完整模型架構
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})
)
引用與作者
@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}
}
📄 許可證
本項目採用 Apache-2.0 許可證。