Transformer: PyTorch Implementation of "Attention Is All You Need"

A PyTorch native platform for training generative AI models

🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!

Minimal reproduction of DeepSeek R1-Zero

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 🍓 and reasoning techniques.

Sky-T1: Train your own O1 preview model within $450

Utilities intended for use with Llama models.

整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。

verl: Volcano Engine Reinforcement Learning for LLMs

slime is an LLM post-training framework for RL Scaling.