从0到1构建一个MiniLLM (pretrain+sft+dpo实践中)

An unnecessarily tiny implementation of GPT-2 in NumPy.

Llama中文社区，实时汇总最新Llama学习资料，构建最好的中文Llama大模型开源生态，完全开源可商用

An easy-to-use Python framework to generate adversarial jailbreak prompts.

LLM training in simple, raw C/CUDA

A collection of GPT system prompts and various prompt injection/leaking knowledge.