# electra-kor-base

**Repository Path**: modelee/electra-kor-base

## Basic Information

- **Project Name**: electra-kor-base
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: main
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 3
- **Forks**: 0
- **Created**: 2023-05-24
- **Last Updated**: 2025-06-26

## Categories & Tags

**Categories**: llm

**Tags**: None

## README

---
language: ko
---

# Electra base model for Korean

* 70GB Korean text dataset and 42000 lower-cased subwords are used
* Check the model performance and other language models for Korean in [github](https://github.com/kiyoungkim1/LM-kor)

```python
from transformers import ElectraTokenizerFast, ElectraModel

tokenizer_electra = ElectraTokenizerFast.from_pretrained("kykim/electra-kor-base")
model = ElectraModel.from_pretrained("kykim/electra-kor-base")
```