Stars
Umami is a modern, privacy-focused analytics platform. An open-source alternative to Google Analytics, Mixpanel and Amplitude.
Blind&Invisible Watermark ，图片盲水印，提取水印无须原图！
The most intuitive desktop API client. Organize and execute REST, GraphQL, WebSockets, Server Sent Events, and gRPC 🦬
FlexAttention based, minimal vllm-style inference engine for fast Gemma 2 inference.
gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI
Wan: Open and Advanced Large-Scale Video Generative Models
Robust recipes to align language models with human and AI preferences
Containerization is a Swift package for running Linux containers on macOS.
Anthropic's Interactive Prompt Engineering Tutorial
Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
Code and YAML files for Getting Started with Kubernetes video course on Pluralsight
Fully Local Manus AI. No APIs, No $200 monthly bills. Enjoy an autonomous agent that thinks, browses the web, and code for the sole cost of electricity. 🔔 Official updates only via twitter @Martin9…
Production-Grade Container Scheduling and Management
Cloud provider for KIND clusters
MicroK8s is a small, fast, single-package Kubernetes for datacenters and the edge.
OpenAI API官方使用指南（中文修订版）Examples and guides for using the OpenAI API（Chinese）
System that uses a hybrid of Genetic Algorithms and Neural Networks to optimize resource allocation under constraints. It features real-time solution visualization, auto-saving of results, and conf…
A complete pipeline for training and evaluating models on the MNIST dataset using knowledge distillation. It involves a teacher model, a regular student model, and a distilled student model.
In this project, I applied advanced deep learning techniques for model optimization, including adaptive learning rates, data normalization, and tuning on a noisy sine wave dataset. SGD and Adam opt…
In this project, I implemented a PyTorch-trained MNIST digit classifier and hosted it as a REST API using the Gin framework in Go. Users can upload an image and get the predicted digit with probabi…
Building on REINFORCE's foundation, this project creates more stable RL agent for grid navigation by adding PPO clipping and KL penalties. The enhanced algorithm helps an 8×8 grid agent learn effic…
Building an LLM with RLHF involves fine-tuning using human-labeled preferences. Based on Learning to Summarize from Human Feedback, it uses supervised learning, reward modeling, and PPO to improve …
A Datacenter Scale Distributed Inference Serving Framework