Nli Deberta Base

🚀 自然語言推理跨編碼器

本模型利用SentenceTransformers的跨編碼器類進行訓練，可用於自然語言推理任務，對給定句子對輸出對應標籤的分數。

📦 安裝指南

文檔未提及具體安裝步驟，可參考SentenceTransformers和transformers庫的官方安裝說明。

✨ 主要特性

• 基於SentenceTransformers的跨編碼器類訓練，可處理自然語言推理任務。
• 針對給定句子對，輸出對應“矛盾”“蘊含”“中立”三個標籤的分數。
• 可用於零樣本分類任務。

📚 詳細文檔

訓練數據

該模型在SNLI和MultiNLI數據集上進行訓練。對於給定的句子對，它將輸出對應三個標籤（矛盾、蘊含、中立）的分數。

性能表現

評估結果請參考 SBERT.net - 預訓練跨編碼器。

💻 使用示例

基礎用法

使用預訓練模型的示例代碼如下：

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)]

高級用法

直接使用Transformers庫（不使用SentenceTransformers庫）的示例代碼如下：

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)

零樣本分類用法

該模型還可用於零樣本分類任務，示例代碼如下：

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)

📄 許可證

本模型採用apache-2.0許可證。

📋 模型信息