Language Models
Morizeyao/GPT2-Chinese
▲ +2 ★ this week
Chinese version of GPT2 training code, using BERT tokenizer.
🧠 Natural Language Processing
PythonMITupdated Apr 25, 2024
基于GOOGLE T5中文生成式模型的摘要生成/指代消解,支持batch批量生成,多进程
$ git clone https://github.com/SunnyGJing/t5-pegasus-chinese.git▲ +2 ★ this week
Chinese version of GPT2 training code, using BERT tokenizer.
A Large-scale Chinese Short-Text Conversation Dataset and Chinese pre-training dialog models
GPT2 for Multiple Languages, including pretrained models. GPT2 多语言支持, 15亿参数中文预训练模型
Pre-trained Chinese ELECTRA(中文ELECTRA预训练模型)
Chinese NewsTitle Generation Project by GPT2.带有超级详细注释的中文GPT2新闻标题生成项目。
TextBox 2.0 is a text generation library with pre-trained language models
Data from GitHub · snapshot Nov 13, 2026