Stars
A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training
ๅผๆญฅๅพไนฆ๏ผใๅคงๆจกๅๅบ็จๅผๅ ๅจๆๅAI Agentใ - ่ฟๆฏไธไบ้ๅธธ็ฎๅ็ๅ ฅ้จ็คบไพ๏ผ้ๅจๅผๅฏผๆฐๆๅ ฅ้จ๏ผ็ฎๅLLMๅผๅ้ขๅๅๅฑๅพๅฟซ๏ผๆฌไนฆๅชๆฏไธไธชๆ็บฒๆ้ขใๆดๅค็็คบไพๅไปฃ็ ๅคงๅฎถๅฏไปฅๅปOpenAI Cookbook, LangChain Exampleไธญๅปๆๆใ
Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.
Kubernetes (k8s) device plugin to enable registration of AMD GPU to a container cluster
้ ๅ HAI Platform ไฝฟ็จ็้ๆๅ็จๆท็้ข
ไธ็งไปปๅก็บงGPU็ฎๅๅๆถ่ฐๅบฆ็้ซๆง่ฝๆทฑๅบฆๅญฆไน ่ฎญ็ปๅนณๅฐ
๐ค Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
PySpark Code for Hands-on Learners
๐ OpenHands: Code Less, Make More
A programming framework for agentic AI ๐ค PyPi: autogen-agentchat Discord: https://aka.ms/autogen-discord Office Hour: https://aka.ms/autogen-officehour
AG2 (formerly AutoGen): The Open-Source AgentOS. Join us at: https://discord.gg/pAbnFJrkgZ
A one stop repository for generative AI research updates, interview resources, notebooks and much more!
Open-sourced, Fast and Context-aware Action Grounding from GUI Instructions for GUI/Computer-use Agents
Allegro is a powerful text-to-video model that generates high-quality videos up to 6 seconds at 15 FPS and 720p resolution from simple text input.
The simplest, fastest repository for training/finetuning medium-sized GPTs.
This repo is meant to serve as a guide for Machine Learning/AI technical interviews.
๐ค ๐๐ฒ๐ฎ๐ฟ๐ป for ๐ณ๐ฟ๐ฒ๐ฒ how to ๐ฏ๐๐ถ๐น๐ฑ an end-to-end ๐ฝ๐ฟ๐ผ๐ฑ๐๐ฐ๐๐ถ๐ผ๐ป-๐ฟ๐ฒ๐ฎ๐ฑ๐ ๐๐๐ & ๐ฅ๐๐ ๐๐๐๐๐ฒ๐บ using ๐๐๐ ๐ข๐ฝ๐ best practices: ~ ๐ด๐ฐ๐ถ๐ณ๐ค๐ฆ ๐ค๐ฐ๐ฅ๐ฆ + 12 ๐ฉ๐ข๐ฏ๐ฅ๐ด-๐ฐ๐ฏ ๐ญ๐ฆ๐ด๐ด๐ฐ๐ฏ๐ด
่ฏฅไปๅบไธป่ฆ่ฎฐๅฝ ๅคงๆจกๅ๏ผLLMs๏ผ ็ฎๆณๅทฅ็จๅธ็ธๅ ณ็้ข่ฏ้ข
ไธป่ฆ่ฎฐๅฝๅคง่ฏญ่จๅคงๆจกๅ๏ผLLMs๏ผ ็ฎๆณ๏ผๅบ็จ๏ผๅทฅ็จๅธ็ธๅ ณ็็ฅ่ฏๅ้ข่ฏ้ข
Use Prometheus to monitor Kubernetes and applications running on Kubernetes
Production-Grade Container Scheduling and Management
ๆฌไปๅบๅฐPyTorchๅฎๆนไนฆ็ฑใDeep learning with PyTorchใ๏ผๅบๆฌๆๅฝ็๏ผ็ฟป่ฏๆไธญๆ็ๅนถ็ปๅบๅฏ่ฟ่ก็็ธๅ ณไปฃ็ ใ
Robust recipes to align language models with human and AI preferences
Ongoing research training transformer models at scale
Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.