Distiluse Base Multilingual Cased V2 Finetuned Stsb Multi Mt Es

🚀 Distiluse-m-v2：針對西班牙語語義文本相似度在stsb_multi_mt上微調的模型

本模型是一個 sentence-transformers 模型（distiluse-base-multilingual-cased-v2），它能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

📦 安裝指南

若你已安裝 sentence-transformers，使用此模型將十分便捷：

pip install -U sentence-transformers

💻 使用示例

基礎用法

使用 sentence-transformers 庫調用模型：

from sentence_transformers import SentenceTransformer
sentences = ["Nerea va a comprar un cuadro usando bitcoins", "Se puede comprar arte con bitcoins"]

model = SentenceTransformer('mrm8488/distiluse-base-multilingual-cased-v2-finetuned-stsb_multi_mt-es')
embeddings = model.encode(sentences)
print(embeddings)

高級用法

若未安裝 sentence-transformers，可以按以下方式使用模型：首先將輸入數據傳入 Transformer 模型，然後對上下文詞嵌入應用合適的池化操作。

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 = ["Nerea va a comprar un cuadro usando bitcoins", "Se puede comprar arte con bitcoins"]

# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('mrm8488/distiluse-base-multilingual-cased-v2-finetuned-stsb_multi_mt-es')
model = AutoModel.from_pretrained('mrm8488/distiluse-base-multilingual-cased-v2-finetuned-stsb_multi_mt-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, mean pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])

print("Sentence embeddings:")
print(sentence_embeddings)

📚 詳細文檔

🔧 技術細節

評估方法

from datasets import load_dataset
from sentence_transformers import SentenceTransformer, InputExample
from sentence_transformers.evaluation import EmbeddingSimilarityEvaluator

 
test_data = load_dataset('stsb_multi_mt', 'es', split='test')
test_data = test_data.rename_columns({'similarity_score': 'label'})
test_data = test_data.map(lambda x: {'label': x['label'] / 5.0})

samples = []
for sample in test_data:
    samples.append(InputExample(
        texts=[sample['sentence1'], sample['sentence2']],
        label=sample['label']
    ))
    
evaluator = EmbeddingSimilarityEvaluator.from_input_examples(
    samples, write_csv=False
)

model = SentenceTransformer('mrm8488/distiluse-base-multilingual-cased-v2-finetuned-stsb_multi_mt-es')

evaluator(model)

# It outputs: 0.7604056195656299

評估結果

斯皮爾曼等級相關性：0.7604056195656299 若要對該模型進行自動評估，請參考 Sentence Embeddings Benchmark：https://seb.sbert.net

訓練參數

• 數據加載器： sentence_transformers.datasets.NoDuplicatesDataLoader.NoDuplicatesDataLoader，長度為 906，參數如下：

  {'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": 3,
      "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": 271,
      "weight_decay": 0.01
  }
  

完整模型架構

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