CLUEbenchmark/CLUE
Chinese Language Understanding Evaluation benchmark providing datasets, baselines, pre-trained models, and leaderboard for evaluating NLP models.
Not currently ranked — collecting fresh signals.
star history
CLUE is a comprehensive Chinese NLP benchmark that provides datasets, pre-trained models, baselines, and leaderboards for evaluating language models on various NLU tasks. The repository includes popular models like BERT, RoBERTa, ALBERT adapted for Chinese, along with evaluation datasets covering classification, inference, and other NLP tasks. It supports multiple deep learning frameworks including PyTorch, TensorFlow, and PaddlePaddle.
Frequently asked
- What is CLUEbenchmark/CLUE?
- Chinese Language Understanding Evaluation benchmark providing datasets, baselines, pre-trained models, and leaderboard for evaluating NLP models.
- Is CLUE open source?
- Yes — CLUEbenchmark/CLUE is an open-source project tracked on heatdrop.
- What language is CLUE written in?
- CLUEbenchmark/CLUE is primarily written in Python.
- How popular is CLUE?
- CLUEbenchmark/CLUE has 4.3k stars on GitHub.
- Where can I find CLUE?
- CLUEbenchmark/CLUE is on GitHub at https://github.com/CLUEbenchmark/CLUE.