Klue Roberta Base Kornli

🚀 klue-roberta-base-kornli

• A model trained on a Korean dataset.
• It takes a premise sentence and a hypothesis sentence as input.
• English can be used, but high accuracy is not guaranteed.
• If the context exceeds 1200 characters, it may be truncated, leading to sub - optimal results.

klue-roberta-base-kornli DEMO: Ainize DEMO

klue-roberta-base-kornli API: Ainize API

🚀 Quick Start

This model is designed to handle Korean language tasks. You can access its demo and API through the provided links.

✨ Features

• Trained on a Korean dataset, suitable for Korean language processing.
• Accepts premise and hypothesis sentences as input.
• Allows English input, though accuracy may be limited.

📚 Documentation

Overview

💻 Usage Examples

Basic Usage

from transformers import AutoTokenizer, pipeline

tokenizer = AutoTokenizer.from_pretrained("ehdwns1516/klue-roberta-base-kornli")

classifier = pipeline(
    "text-classification",
    model="ehdwns1516/klue-roberta-base-kornli",
    return_all_scores=True,
)

premise = "your premise"
hypothesis = "your hypothesis"

result = dict()
result[0] = classifier(premise + tokenizer.sep_token + hypothesis)[0]

⚠️ Important Note

If the context is longer than 1200 characters, the context may be cut in the middle and the result may not come out well.

💡 Usage Tip

You can use English, but don't expect high accuracy as the model is trained on a Korean dataset.