Ko Sroberta Sts

🚀 韓語語義相似度模型 ko - sroberta - sts

ko - sroberta - sts 是一個基於 sentence - transformers 的模型，它能夠將句子和段落映射到 768 維的密集向量空間中，可用於聚類、語義搜索等任務。

🚀 快速開始

安裝依賴

若要使用該模型，需要安裝 sentence - transformers：

pip install -U sentence-transformers

模型使用

基礎用法

使用 sentence - transformers 庫調用模型：

from sentence_transformers import SentenceTransformer
sentences = ["안녕하세요?", "한국어 문장 임베딩을 위한 버트 모델입니다."]

model = SentenceTransformer('jhgan/ko-sroberta-sts')
embeddings = model.encode(sentences)
print(embeddings)

高級用法

若不使用 sentence - transformers，可以按以下方式使用模型：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 = ['This is an example sentence', 'Each sentence is converted']

# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('jhgan/ko-sroberta-sts')
model = AutoModel.from_pretrained('jhgan/ko-sroberta-sts')

# 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

該模型在 KorSTS 訓練數據集上進行訓練，並在 KorSTS 評估數據集上進行評估，結果如下：

訓練參數

數據加載器

使用 torch.utils.data.dataloader.DataLoader，長度為 719，參數如下：

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

損失函數

使用 sentence_transformers.losses.CosineSimilarityLoss.CosineSimilarityLoss。

訓練方法參數

{
    "epochs": 5,
    "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": 360,
    "weight_decay": 0.01
}

完整模型架構

SentenceTransformer(
  (0): Transformer({'max_seq_length': 128, '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

如需更多信息，請參考相關引用資料。