KoELECTRA-small-v3-modu-ner is a token classification model hosted on Hugging Face. It is a small Korean ELECTRA variant that has been fine-tuned for named entity recognition tasks on the MODU dataset.
The model accepts Korean text and assigns labels to individual tokens to identify named entities. It is distributed in PyTorch format along with Safetensors weights and includes TensorBoard training metrics. Users load it through the Transformers library either via a high-level pipeline for token-classification or by directly instantiating AutoTokenizer and AutoModelForTokenClassification.
The repository provides example code for both usage patterns and lists inference options that include notebooks on Google Colab and Kaggle. It is made available for direct download and can be deployed to compatible inference providers. The model card outlines intended uses and limitations along with training details, though specific performance numbers are not shown on the main page.
No pricing information appears because the model is offered as an open artifact on the Hugging Face platform. The page indicates it was generated from the Trainer API and carries standard repository features such as community discussion and versioned files.
KoELECTRA Small V3 Modu Ner sits in PulseGate's Other AI category. It focuses on identifying and classifying named entities in Korean text for NLP applications. It is built as an open-source project for developers. The project is open source (Open Source). It runs on the web and API.
Leo97 builds and maintains KoELECTRA Small V3 Modu Ner, and it first shipped in 2022. Key capabilities include Named Entity Recognition, Korean Language Support, and Token Classification. It exposes integrations via a public API.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do