Nli Deberta Base

🚀 自然语言推理跨编码器

本模型利用SentenceTransformers的跨编码器类进行训练，可用于自然语言推理任务，对给定句子对输出对应标签的分数。

📦 安装指南

文档未提及具体安装步骤，可参考SentenceTransformers和transformers库的官方安装说明。

✨ 主要特性

• 基于SentenceTransformers的跨编码器类训练，可处理自然语言推理任务。
• 针对给定句子对，输出对应“矛盾”“蕴含”“中立”三个标签的分数。
• 可用于零样本分类任务。

📚 详细文档

训练数据

该模型在SNLI和MultiNLI数据集上进行训练。对于给定的句子对，它将输出对应三个标签（矛盾、蕴含、中立）的分数。

性能表现

评估结果请参考 SBERT.net - 预训练跨编码器。

💻 使用示例

基础用法

使用预训练模型的示例代码如下：

from sentence_transformers import CrossEncoder
model = CrossEncoder('cross-encoder/nli-deberta-base')
scores = model.predict([('A man is eating pizza', 'A man eats something'), ('A black race car starts up in front of a crowd of people.', 'A man is driving down a lonely road.')])

#Convert scores to labels
label_mapping = ['contradiction', 'entailment', 'neutral']
labels = [label_mapping[score_max] for score_max in scores.argmax(axis=1)]

高级用法

直接使用Transformers库（不使用SentenceTransformers库）的示例代码如下：

from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch

model = AutoModelForSequenceClassification.from_pretrained('cross-encoder/nli-deberta-base')
tokenizer = AutoTokenizer.from_pretrained('cross-encoder/nli-deberta-base')

features = tokenizer(['A man is eating pizza', 'A black race car starts up in front of a crowd of people.'], ['A man eats something', 'A man is driving down a lonely road.'],  padding=True, truncation=True, return_tensors="pt")

model.eval()
with torch.no_grad():
    scores = model(**features).logits
    label_mapping = ['contradiction', 'entailment', 'neutral']
    labels = [label_mapping[score_max] for score_max in scores.argmax(dim=1)]
    print(labels)

零样本分类用法

该模型还可用于零样本分类任务，示例代码如下：

from transformers import pipeline

classifier = pipeline("zero-shot-classification", model='cross-encoder/nli-deberta-base')

sent = "Apple just announced the newest iPhone X"
candidate_labels = ["technology", "sports", "politics"]
res = classifier(sent, candidate_labels)
print(res)

📄 许可证

本模型采用apache-2.0许可证。

📋 模型信息