COS TAPT N RoBERTa Sts E3 OnlineContrastiveLoss 2023 10 16

🚀 {MODEL_NAME}

這是一個 sentence-transformers 模型：它可以將句子和段落映射到一個 1024 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

本模型可以通過 sentence-transformers 或 HuggingFace Transformers 兩種方式使用，下面為你詳細介紹。

📦 安裝指南

若要使用 sentence-transformers 調用模型，需要先安裝相關庫：

pip install -U sentence-transformers

💻 使用示例

基礎用法（Sentence-Transformers）

安裝好 sentence-transformers 後，你可以按照以下方式使用模型：

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)

高級用法（HuggingFace Transformers）

若未安裝 sentence-transformers，你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('{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)

📚 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

訓練參數

該模型的訓練參數如下：

數據加載器： torch.utils.data.dataloader.DataLoader，長度為 75，參數如下：

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

損失函數： sentence_transformers.losses.OnlineContrastiveLoss.OnlineContrastiveLoss

fit() 方法的參數：

{
    "epochs": 3,
    "evaluation_steps": 1000,
    "evaluator": "sentence_transformers.evaluation.EmbeddingSimilarityEvaluator.EmbeddingSimilarityEvaluator",
    "max_grad_norm": 1,
    "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
    "optimizer_params": {
        "lr": 2e-05
    },
    "scheduler": "WarmupLinear",
    "steps_per_epoch": null,
    "warmup_steps": 23,
    "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': 1024, '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