Eli5 All Mpnet Base V2

🚀 addy88/eli5-all-mpnet-base-v2 句子相似度模型

這是一個sentence-transformers模型，它可以將句子和段落映射到一個768維的密集向量空間，可用於聚類或語義搜索等任務。該模型在ELI5數據集上進行了微調。

🚀 快速開始

本模型可通過兩種方式使用，分別是藉助 sentence-transformers 庫和直接使用 HuggingFace Transformers 庫。下面為你詳細介紹這兩種使用方法。

📦 安裝指南

若要使用 sentence-transformers 庫，你需要先安裝它：

pip install -U sentence-transformers

💻 使用示例

基礎用法（Sentence-Transformers）

當你安裝了 sentence-transformers 庫後，使用該模型會變得非常簡單：

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

model = SentenceTransformer('addy88/eli5-all-mpnet-base-v2')
embeddings = model.encode(sentences)
print(embeddings)

高級用法（HuggingFace Transformers）

如果你沒有安裝 sentence-transformers 庫，也可以使用該模型。首先，你需要將輸入數據傳入 Transformer 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


#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('addy88/eli5-all-mpnet-base-v2')
model = AutoModel.from_pretrained('addy88/eli5-all-mpnet-base-v2')

# 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)

📚 詳細文檔

評估結果

若要對該模型進行自動評估，請參考 Sentence Embeddings Benchmark：https://seb.sbert.net

訓練信息

該模型的訓練參數如下：

數據加載器

sentence_transformers.datasets.NoDuplicatesDataLoader.NoDuplicatesDataLoader，長度為 14393，參數如下：

{'batch_size': 16}

損失函數

sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss，參數如下：

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

fit() 方法的參數

{
    "epochs": 1,
    "evaluation_steps": 0,
    "evaluator": "NoneType",
    "max_grad_norm": 1,
    "optimizer_class": "<class 'transformers.optimization.AdamW'>",
    "optimizer_params": {
        "lr": 2e-05
    },
    "scheduler": "WarmupLinear",
    "steps_per_epoch": null,
    "warmup_steps": 1439,
    "weight_decay": 0.01
}

完整模型架構

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: RobertaModel 
  (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

該模型由 sentence-transformers 團隊訓練。

如果你覺得這個模型很有用，請引用我們的論文 Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks：

@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 = "http://arxiv.org/abs/1908.10084",
}