用于从头预训练+SFT一个小参数量的中文LLaMa2的仓库;24G单卡即可运行得到一个具备简单中文问答能力的chat-llama2.
Like DLLXW/baby-llama2-chinese, 0 likes 0 Bookmark DLLXW/baby-llama2-chinese, 0 bookmarks 0 A 124.6M LLM trained from scratch on 13B tokens on a single RTX 4090 — tokenizer, pretraining, post-training, evaluation, and reproducible inference.
Like yangqi0/petitgpt, 0 likes 0 Bookmark yangqi0/petitgpt, 0 bookmarks 0 The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.
Like jzhang38/TinyLlama, 0 likes 0 Bookmark jzhang38/TinyLlama, 0 bookmarks 0 🧠 Train a 64M-parameter LLM from scratch in just 2h!
Like jingyaogong/minimind, 5 likes 5 Bookmark jingyaogong/minimind, 7 bookmarks 7 中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)
Like ymcui/Chinese-LLaMA-Alpaca, 0 likes 0 Bookmark ymcui/Chinese-LLaMA-Alpaca, 0 bookmarks 0 [Kaggle-2nd] Lightweight yet Effective Traditional Chinese LLM.
Like zake7749/Kyara, 0 likes 0 Bookmark zake7749/Kyara, 0 bookmarks 0 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
Like CVI-SZU/Linly, 0 likes 0 Bookmark CVI-SZU/Linly, 0 bookmarks 0 中文羊驼大模型三期项目 (Chinese Llama-3 LLMs) developed from Meta Llama 3
Like ymcui/Chinese-LLaMA-Alpaca-3, 0 likes 0 Bookmark ymcui/Chinese-LLaMA-Alpaca-3, 0 bookmarks 0