{gte-tiny}

这是一个 sentence-transformers 模型：它将句子和段落映射到 384 维的密集向量空间，可用于聚类或语义搜索等任务。 它是从 thenlper/gte-small 蒸馏而来，性能相当（约一半大小，略有下降）。

<!--- 在此描述您的模型 -->

使用方法 (Sentence-Transformers)

当您安装了 sentence-transformers 后，使用此模型变得非常简单：

pip install -U sentence-transformers

然后您可以这样使用该模型：

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)

使用方法 (HuggingFace Transformers)

如果没有 sentence-transformers，您可以这样使用该模型：首先将输入传递给 transformer 模型，然后需要在上下文词嵌入之上应用正确的池化操作。

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)

评估结果

<!--- 描述您的模型是如何被评估的 -->

关于此模型的自动化评估，请参阅 Sentence Embeddings Benchmark：https://seb.sbert.net

完整模型架构

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)

引用与作者

<!--- 描述在哪里可以找到更多信息 -->