SKTBrain/KoBERT
KoBERT is a Korean pre-trained BERT model developed by SKTBrain, trained on 5M sentences from Korean Wikipedia.
Not currently ranked — collecting fresh signals.
star history
KoBERT is a Korean-specific pre-trained BERT model trained on Korean Wikipedia (5M sentences, 54M words) using PyTorch and Hugging Face Transformers. It provides a base-sized cased BERT architecture with 12 layers, 768 hidden units, and 12 attention heads, including a SentencePiece tokenizer with 8,002 vocab size. The model supports NLP tasks including sentiment analysis, named entity recognition, and sentence embeddings, and can be used via PyTorch, ONNX, or MXNet-Gluon.
Frequently asked
- What is SKTBrain/KoBERT?
- KoBERT is a Korean pre-trained BERT model developed by SKTBrain, trained on 5M sentences from Korean Wikipedia.
- Is KoBERT open source?
- Yes — SKTBrain/KoBERT is open source, released under the Apache-2.0 license.
- What language is KoBERT written in?
- SKTBrain/KoBERT is primarily written in Python.
- How popular is KoBERT?
- SKTBrain/KoBERT has 1.4k stars on GitHub.
- Where can I find KoBERT?
- SKTBrain/KoBERT is on GitHub at https://github.com/SKTBrain/KoBERT.