Tom Gou

minimind. 🧠「大模型」2小时完全从0训练64M的小参数LLM！Train a 64M-parameter LLM from scratch in just 2h!

Tensor-Puzzles. Solve puzzles. Improve your pytorch.

dmls-book. Summaries and resources for Designing Machine Learning Systems book (Chip Huyen, O'Reilly 2022)

notchprompt. distraction-free teleprompter hidden in the macbook notch

LLM-Interview-Questions-and-Answers-Hub. 100+ LLM interview questions with answers.

al-folio. A beautiful, simple, clean, and responsive Jekyll theme for academics

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

TorchCode. 🔥 LeetCode for PyTorch — practice implementing softmax, attention, GPT-2 and more from scratch with instant auto-grading. Jupyter-based, self-hosted or try online.

tokenspeed. TokenSpeed is a speed-of-light LLM inference engine.

llm-scaling-notes. Self-study notes and extensions on JAX/ML scaling, transformer systems, and LLM serving.

claude-code. Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.

obsidian-skills. Agent skills for Obsidian. Teach your agent to use Obsidian CLI and open formats including Markdown, Bases, JSON Canvas.

mindflow. TypeScript

nanochat. The best ChatGPT that $100 can buy.

autoresearch. AI agents running research on single-GPU nanochat training automatically

awesome-VLLMs. This repository collects papers on VLLM applications. We will update new papers irregularly.

Awesome-VLA. Paper Survey for Visual Language Action

openclaw. Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

alpamayo. NVIDIA Alpamayo 1 Nano is an open 10B reasoning VLA model for autonomous vehicles that pairs driving trajectories with Chain-of-Causation reasoning.

AlohaMini. Open-Source Dual-Arm Mobile Robot with Motorized Lift

TensorRT-LLM. TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way.

us-visa-bot. US Visa Bot

scaling-book. Home for "How To Scale Your Model", a short blog-style textbook about scaling LLMs on TPUs

nanoVLM. The simplest, fastest repository for training/finetuning small-sized VLMs.

happy-llm. 📚 从零开始构建大模型

lectures. Python

SO-ARM100. Standard Open Arm 100

End-to-End-Autonomous-Driving. A collection of recent resources on End-to-End Autonomous Driving [survey accepted in IEEE TIV]

anime. JavaScript animation engine

LeKiwi. LeKiwi - Low-Cost Mobile Manipulator

OpenEMMA. OpenEMMA, a permissively licensed open source "reproduction" of Waymo’s EMMA model.

lerobot. 🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

Halo-iOS. iOS companion app for COLMI Ring

gitbook. The open source frontend for GitBook doc sites

MLOps-Basics. Jupyter Notebook

ChatPaper. Use ChatGPT to summarize the arXiv papers. 全流程加速科研，利用chatgpt进行论文全文总结+专业翻译+润色+审稿+审稿回复

generative-ai-for-beginners. 21 Lessons, Get Started Building with Generative AI

neovis.js. Neo4j + vis.js = neovis.js. Graph visualizations in the browser with data from Neo4j.

LLM101n. LLM101n: Let's build a Storyteller

llm-graph-builder. Neo4j graph construction from unstructured data using LLMs

phoenix. AI Observability & Evaluation

autogen. A programming framework for agentic AI

OpenGlass. Turn any glasses into AI-powered smart glasses

nextra. Simple, powerful and flexible site generation framework with everything you love from Next.js.

ComfyUI_TensorRT. Python

ComfyUI. The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

ChatGPTSwiftUI. A ChatGPT native iOS, macOS, watchOS, tvOS SwiftUI Application

audio_exp. just my random experiments with audio data processing and deep learning models

whispercpp. Pybind11 bindings for Whisper.cpp

gpt_academic. 为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, moss等。

Wonder3D. Single Image to 3D using Cross-Domain Diffusion for 3D Generation

langroid. Harness LLMs with Multi-Agent Programming

SEED. Official implementation of SEED-LLaMA (ICLR 2024).

LLaVA. [NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

deep-chat. Fully customizable AI chatbot component for your website

camel. 🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org

Awesome-LLMOps. An awesome & curated list of best LLMOps tools for developers

litellm. The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]

sec-insights. A real world full-stack application using LlamaIndex

pokemon-showdown. Pokémon battle simulator.

chatbot. A full-featured, hackable Next.js AI chatbot built by Vercel

openinterpreter. A coding agent for open models like Kimi K3

AgentVerse. 🤖 AgentVerse 🪐 is designed to facilitate the deployment of multiple LLM-based agents in various applications, which primarily provides two frameworks: task-solving and simulation

ai-town. A MIT-licensed, deployable starter kit for building and customizing your own version of AI town - a virtual town where AI characters live, chat and socialize.

generative_agents. Generative Agents: Interactive Simulacra of Human Behavior

humaneval-langchain. Benchmark results from code generation with LLMs

github-readme-stats. :zap: Dynamically generated stats for your github readmes

llama2.c. Inference Llama 2 in one file of pure C

localGPT. Chat with your documents on your local device using GPT models. No data leaves your device and 100% private.

OpenLLM. Run any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud.

llama-cookbook. Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services

RealChar. 🎙️🤖Create, Customize and Talk to your AI Character/Companion in Realtime (All in One Codebase!). Have a natural seamless conversation with AI everywhere (mobile, web and terminal) using LLM OpenAI GPT3.5/4, Anthropic Claude2, Chroma Vector DB, Whisper Speech2Text, ElevenLabs Text2Speech🎙️🤖

stable-diffusion-webui. Stable Diffusion web UI

llama_index. LlamaIndex is the leading document agent and OCR platform

chatgpt-google-summary-extension. Chrome extension to view ChatGPT summaries alongside Google search results and YouTube videos, also supports Yahoo! ニュース、PubMed、PMC、NewsPicks、Github、Nikkei、 Bing、Google Patents, and any page summary.

chatgpt-google-extension. This project is deprecated. Check my new project ChatHub:

ChatGPT. ❄️ ChatGPT Desktop Application (Mac, Windows and Linux)

prompts.chat. f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

openDogV3. C++

Tetris-AI. Tetris AI implemented using Flask and JavaScript. Work in progress.

penkesu. Penkesu Computer - A Homebrew Retro-style Handheld PC

gclx-official. 国产良心官方网站代码

minty. a minimal NFT minting platform using IPFS

nft-image-generator. Jupyter Notebook

react-nft-template. A template for a nft website with minting functionality

pyxelate. Python class that generates pixel art from images

spark-movie-lens. An on-line movie recommender using Spark, Python Flask, and the MovieLens dataset

python-spark-recsys. An example Python ALS recommender system

img2ascii. Python

oreilly-generator. oreilly-generator

deeplearningbook-chinese. Deep Learning Book Chinese Translation

core. :house_with_garden: Open source home automation that puts local control and privacy first.

pix2code. pix2code: Generating Code from a Graphical User Interface Screenshot

convnet-benchmarks. Easy benchmarking of all publicly accessible implementations of convnets

DeepLearningTutorials. Deep Learning Tutorial notes and code. See the wiki for more info.

awesome-vue. 🎉 A curated list of awesome things related to Vue.js