一个为零样本和小样本文本分类训练的连体网络模型。

基础模型是 xlm-roberta-base 。它被训练在 SNLI 、 MNLI 、 ANLI 和 XNLI 上。

这是一个 sentence-transformers 模型：它将句子和段落映射到一个768维稠密向量空间。

用法（Sentence-Transformers）

在安装了 sentence-transformers 之后，使用这个模型变得很容易：

pip install -U sentence-transformers

然后你可以像这样使用这个模型：

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)

用法（HuggingFace Transformers）

没有 sentence-transformers ，你可以像这样使用这个模型：首先，将你的输入通过变形器模型，然后在上下文化的词嵌入之上应用正确的汇集操作。

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)