🚀 {MODEL_NAME}
這是一個sentence-transformers模型,它可以將句子和段落映射到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
本模型可以通過兩種方式使用,下面為你詳細介紹。
📦 安裝指南
如果你安裝了sentence-transformers,使用這個模型會變得非常簡單:
pip install -U sentence-transformers
💻 使用示例
基礎用法(Sentence-Transformers)
安裝完成後,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)
如果你沒有安裝sentence-transformers,也可以使用該模型。首先,將輸入數據傳入transformer模型,然後對上下文相關的詞嵌入應用正確的池化操作。
from transformers import AutoTokenizer, AutoModel
import torch
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output[0]
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 = ['This is an example sentence', 'Each sentence is converted']
tokenizer = AutoTokenizer.from_pretrained('{MODEL_NAME}')
model = AutoModel.from_pretrained('{MODEL_NAME}')
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
with torch.no_grad():
model_output = model(**encoded_input)
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
print("Sentence embeddings:")
print(sentence_embeddings)
📚 詳細文檔
評估結果
要對該模型進行自動評估,請參考Sentence Embeddings Benchmark:https://seb.sbert.net
訓練情況
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34061,參數如下:
{'batch_size': 32, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
損失函數:
sentence_transformers.losses.MSELoss.MSELoss
fit()
方法的參數:
{
"epochs": 1,
"evaluation_steps": 0,
"evaluator": "NoneType",
"max_grad_norm": 1,
"optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
"optimizer_params": {
"eps": 1e-06,
"lr": 2e-05
},
"scheduler": "WarmupLinear",
"steps_per_epoch": null,
"warmup_steps": 3406,
"weight_decay": 0.01
}
完整模型架構
SentenceTransformer(
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: XLMRobertaModel
(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})
)
📄 許可證
本模型採用MIT許可證。
📖 引用與作者