Multi-layer Recurrent Neural Networks (LSTM, GRU, RNN) for character-level language models in Torch. Based on code of https://github.com/karpathy/char-rnn. Support Chinese and other things.
$ git clone https://github.com/zhangzibin/char-rnn-chinese.gitRWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.
大规模中文自然语言处理语料 Large Scale Chinese Corpus for NLP
ChatRWKV is like ChatGPT but powered by RWKV (100% RNN) language model, and open source.
中文语言理解测评基准 Chinese Language Understanding Evaluation Benchmark: datasets, baselines, pre-trained models, corpus and leaderboard
Chinese-LLaMA 1&2、Chinese-Falcon 基础模型；ChatFlow中文对话模型；中文OpenLLaMA模型；NLP预训练/指令微调数据集
青简 Qingjian：用 Rust 写的拼音输入法，候选词旁多一条正在学的语言的译词
Data from GitHub · snapshot Sep 24, 2026