Nli Deberta V3 Xsmall

🚀 自然语言推理跨编码器

本模型用于自然语言推理任务，借助 SentenceTransformers 的 Cross-Encoder 类进行训练。它基于 microsoft/deberta-v3-xsmall 构建，能够对给定的句子对进行推理，输出对应矛盾、蕴含和中立三种标签的分数。

✨ 主要特性

• 基于 microsoft/deberta-v3-xsmall 模型，具有轻量级的特点。
• 可用于自然语言推理任务，输出句子对在矛盾、蕴含和中立三种标签上的得分。
• 支持零样本分类任务。

📦 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。

💻 使用示例

基础用法

from sentence_transformers import CrossEncoder
model = CrossEncoder('cross-encoder/nli-deberta-v3-xsmall')
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

使用 Transformers AutoModel

from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch

model = AutoModelForSequenceClassification.from_pretrained('cross-encoder/nli-deberta-v3-xsmall')
tokenizer = AutoTokenizer.from_pretrained('cross-encoder/nli-deberta-v3-xsmall')

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

from transformers import pipeline

classifier = pipeline("zero-shot-classification", model='cross-encoder/nli-deberta-v3-xsmall')

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

📚 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，模型将输出对应矛盾、蕴含和中立三种标签的分数。

性能表现

• SNLI 测试数据集上的准确率：91.64
• MNLI 不匹配集上的准确率：87.77

更多评估结果，请参考 SBERT.net - 预训练跨编码器。

📄 许可证

本模型使用 apache-2.0 许可证。

📦 信息表格