Transformer language model (GPT-2) with sentencepiece tokenizer
$ git clone https://github.com/lopuhin/transformer-lm.git▲ +2 ★ this week
RWKV (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.
▲ +13 ★ this week
Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
▲ +1 ★ this week
Build, personalize and control your own LLMs. From data pre-processing to fine-tuning, xTuring provides an easy way to personalize open-source LLMs. Join our discord community: https://discord.gg/TgHXuSJEk6
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）
🛸 Use pretrained transformers like BERT, XLNet and GPT-2 in spaCy
Data from GitHub · snapshot Nov 13, 2026