ymcui/Chinese-ELECTRA
Chinese ELECTRA pre-trained language model released by Harbin Institute of Technology and iFlytek (HFL).
Not currently ranked — collecting fresh signals.
star history
This repository provides pre-trained Chinese ELECTRA models developed by the Harbin Institute of Technology and iFlytek joint lab (HFL). ELECTRA uses replaced token detection for pre-training rather than masked language modeling. The Chinese ELECTRA-small model achieves comparable performance to BERT-base while having only 1/10th the parameters. The models support both PyTorch and TensorFlow frameworks.
Frequently asked
- What is ymcui/Chinese-ELECTRA?
- Chinese ELECTRA pre-trained language model released by Harbin Institute of Technology and iFlytek (HFL).
- Is Chinese-ELECTRA open source?
- Yes — ymcui/Chinese-ELECTRA is open source, released under the Apache-2.0 license.
- What language is Chinese-ELECTRA written in?
- ymcui/Chinese-ELECTRA is primarily written in Python.
- How popular is Chinese-ELECTRA?
- ymcui/Chinese-ELECTRA has 1.4k stars on GitHub.
- Where can I find Chinese-ELECTRA?
- ymcui/Chinese-ELECTRA is on GitHub at https://github.com/ymcui/Chinese-ELECTRA.