Starred repositories
The absolute trainer to light up AI agents.
🌐 Make websites accessible for AI agents. Automate tasks online with ease.
A version of verl to support diverse tool use
Agent-R1: Training Powerful LLM Agents with End-to-End Reinforcement Learning
TensorDict is a pytorch dedicated tensor container.
A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.
Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning
Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.
[EMNLP 2025 Demo] PDF scientific paper translation with preserved formats - 基于 AI 完整保留排版的 PDF 文档全文双语翻译,支持 Google/DeepL/Ollama/OpenAI 等服务,提供 CLI/GUI/MCP/Docker/Zotero
Fully open reproduction of DeepSeek-R1
Solve Visual Understanding with Reinforced VLMs
Data processing for and with foundation models! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷
A very simple GRPO implement for reproducing r1-like LLM thinking.
🚀🚀 「大模型」2小时完全从0训练64M的小参数GPT!🌏 Train a 64M-parameter GPT from scratch in just 2h!
LMDeploy is a toolkit for compressing, deploying, and serving LLMs.
《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调(全参数/Lora)、部署国内外开源大模型(LLM)/多模态大模型(MLLM)教程
Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
Firefly: 大模型训练工具,支持训练Qwen2.5、Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya2、Vicuna、Bloom等大模型
Unsupervised text tokenizer for Neural Network-based text generation.
Coding a Multimodal (Vision) Language Model from scratch in PyTorch with full explanation: https://www.youtube.com/watch?v=vAmKB7iPkWw
The simplest, fastest repository for training/finetuning medium-sized GPTs.
A Framework of Small-scale Large Multimodal Models
tiktoken is a fast BPE tokeniser for use with OpenAI's models.
Natural Language Processing Best Practices & Examples
✨✨Latest Advances on Multimodal Large Language Models
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step