Sentence Similarity Spanish Es

🚀 hiiamsid/sentence_similarity_spanish_es

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。

🚀 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 HuggingFace Transformers 庫。下面將詳細介紹這兩種使用方法。

📦 安裝指南

若要使用 sentence-transformers 庫調用本模型，需先安裝該庫：

pip install -U sentence-transformers

💻 使用示例

基礎用法（使用 sentence-transformers）

from sentence_transformers import SentenceTransformer
sentences = ['Mi nombre es Siddhartha', 'Mis amigos me llamaron por mi nombre Siddhartha']

model = SentenceTransformer('hiiamsid/sentence_similarity_spanish_es')
embeddings = model.encode(sentences)
print(embeddings)

高級用法（使用 HuggingFace Transformers）

若不使用 sentence-transformers 庫，可按以下步驟操作：首先將輸入傳遞給 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 = ['Mi nombre es Siddhartha', 'Mis amigos me llamaron por mi nombre Siddhartha']

# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('hiiamsid/sentence_similarity_spanish_es')
model = AutoModel.from_pretrained('hiiamsid/sentence_similarity_spanish_es')

# 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, max 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

cosine_pearson : 0.8280372842978689
cosine_spearman : 0.8232689765056079
euclidean_pearson : 0.81021993884437
euclidean_spearman : 0.8087904592393836
manhattan_pearson : 0.809645390126291
manhattan_spearman : 0.8077035464970413
dot_pearson : 0.7803662255836028
dot_spearman : 0.7699607641618339

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

該模型使用以下參數進行訓練：

數據加載器： torch.utils.data.dataloader.DataLoader，長度為 360，參數如下：

{'batch_size': 16, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}

損失函數： sentence_transformers.losses.CosineSimilarityLoss.CosineSimilarityLoss

fit() 方法的參數：

{
    "callback": null,
    "epochs": 4,
    "evaluation_steps": 1000,
    "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": 144,
    "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})
)

引用與作者信息

• 數據集：stsb_multi_mt
• 模型：dccuchile/bert-base-spanish-wwm-cased
• 句子轉換器 語義文本相似度

📄 許可證

本模型採用 Apache-2.0 許可證。