🚀 SBERT-base-nli-v2

这个模型被用于论文 "SGPT: GPT Sentence Embeddings for Semantic Search" 和 "TSDAE: Using Transformer-based Sequential Denoising Auto-Encoder for Unsupervised Sentence Embedding Learning" 中，主要用于句子相似度计算、特征提取等任务。

🚀 快速开始

若你想了解使用说明，请参考我们的代码库：https://github.com/Muennighoff/sgpt

若你想查看评估结果，请参考我们的论文：https://arxiv.org/abs/2202.08904

📦 安装指南

当你安装了 sentence-transformers 后，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（Sentence-Transformers）

from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]

model = SentenceTransformer('{MODEL_NAME}')
embeddings = model.encode(sentences)
print(embeddings)

基础用法（HuggingFace Transformers）

如果没有安装 sentence-transformers，你可以按如下方式使用该模型：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。

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 = ['This is an example sentence', 'Each sentence is converted']

# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('{MODEL_NAME}')
model = AutoModel.from_pretrained('{MODEL_NAME}')

# 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)

评估结果

若要对这个模型进行自动评估，请查看 Sentence Embeddings Benchmark：https://seb.sbert.net

🔧 技术细节

训练参数

该模型的训练参数如下：

数据加载器： sentence_transformers.datasets.NoDuplicatesDataLoader.NoDuplicatesDataLoader，长度为 8807，参数如下：

{'batch_size': 64}

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": 1,
    "evaluation_steps": 880,
    "evaluator": "sentence_transformers.evaluation.EmbeddingSimilarityEvaluator.EmbeddingSimilarityEvaluator",
    "max_grad_norm": 1,
    "optimizer_class": "<class 'transformers.optimization.AdamW'>",
    "optimizer_params": {
        "lr": 2e-05
    },
    "scheduler": "WarmupLinear",
    "steps_per_epoch": null,
    "warmup_steps": 881,
    "weight_decay": 0.01
}

完整模型架构

SentenceTransformer(
  (0): Transformer({'max_seq_length': 75, '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})
)

📄 许可证

引用与作者

@article{muennighoff2022sgpt,
  title={SGPT: GPT Sentence Embeddings for Semantic Search},
  author={Muennighoff, Niklas},
  journal={arXiv preprint arXiv:2202.08904},
  year={2022}
}