🚀 imvladikon/sentence-transformers-alephbert[WIP]

这是一个sentence-transformers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。当前版本是在私有语料库上对LaBSE模型进行蒸馏得到的。

🚀 快速开始

安装依赖

如果你安装了sentence-transformers，使用这个模型会变得很容易：

pip install -U sentence-transformers

使用示例

基础用法

from sentence_transformers import SentenceTransformer
from sentence_transformers.util import cos_sim

sentences = [
"הם היו שמחים לראות את האירוע שהתקיים.",
"לראות את האירוע שהתקיים היה מאוד משמח להם."
]

model = SentenceTransformer('imvladikon/sentence-transformers-alephbert')
embeddings = model.encode(sentences)


print(cos_sim(*tuple(embeddings)).item())
# 0.883316159248352

高级用法

如果没有安装sentence-transformers，你可以这样使用该模型：首先，将输入传递给transformer模型，然后对上下文词嵌入应用正确的池化操作。

import torch
from torch import nn
from transformers import AutoTokenizer, AutoModel


#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 = [
"הם היו שמחים לראות את האירוע שהתקיים.",
"לראות את האירוע שהתקיים היה מאוד משמח להם."
]

# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('imvladikon/sentence-transformers-alephbert')
model = AutoModel.from_pretrained('imvladikon/sentence-transformers-alephbert')

# 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'])

cos_sim = nn.CosineSimilarity(dim=0, eps=1e-6)
print(cos_sim(sentence_embeddings[0], sentence_embeddings[1]).item())

📚 详细文档

评估结果

要对该模型进行自动评估，请参阅 Sentence Embeddings Benchmark：https://seb.sbert.net

训练参数

该模型使用以下参数进行训练：

数据加载器

torch.utils.data.dataloader.DataLoader，长度为44999，参数如下：

{'batch_size': 8, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}

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": 10,
    "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": 44999,
    "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

@misc{seker2021alephberta,
      title={AlephBERT:A Hebrew Large Pre-Trained Language Model to Start-off your Hebrew NLP Application With}, 
      author={Amit Seker and Elron Bandel and Dan Bareket and Idan Brusilovsky and Refael Shaked Greenfeld and Reut Tsarfaty},
      year={2021},
      eprint={2104.04052},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

@misc{reimers2019sentencebert,
      title={Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks}, 
      author={Nils Reimers and Iryna Gurevych},
      year={2019},
      eprint={1908.10084},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}