Veld Base

🚀 Veld Base

A pretrained vision encoder text decoder model supporting Korean and English. For more details, refer to Github.

🚀 Quick Start

✨ Features

• Multilingual Support: Supports both English and Korean.
• Pretrained Model: A pre - trained vision encoder text decoder model.
• Image - to - Text: Capable of image - to - text tasks.

📦 Installation

No specific installation steps are provided in the original document.

💻 Usage Examples

Basic Usage

from transformers import AutoProcessor, AutoModel

processor = AutoProcessor.from_pretrained("KETI-AIR/veld-base", trust_remote_code=True)
model = AutoModel.from_pretrained("KETI-AIR/veld-base", trust_remote_code=True)

Advanced Usage

You can use AutoTokenizer and AutoFeatureExtractor instead of AutoProcessor. And you don't need to pass trust_remote_code=True for AutoTokenizer and AutoFeatureExtractor.

from transformers import AutoFeatureExtractor, AutoTokenizer, AutoModel

feature_extractor = AutoFeatureExtractor.from_pretrained("KETI-AIR/veld-base")
tokenizer = AutoTokenizer.from_pretrained("KETI-AIR/veld-base")
model = AutoModel.from_pretrained("KETI-AIR/veld-base", trust_remote_code=True)

📚 Documentation

📄 License

This project is licensed under the Apache - 2.0 license.