Fancy stream processing made operationally mundane. This repository is a fork of the original project before the license was changed.

Easy and fast file sharing from the command-line.

A nanoGPT pipeline packed in a spreadsheet

This project uses an arduino proxy HPE inversed PWM signal to support Noctua and other low-speed silent fans, and providing second fan interface to cool down iLO chip.

WordPress with SQLite, ready to use out of the box.

Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of …

DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

Native Ubuntu installations for Apple silicon hardware

CoreNet: A library for training deep neural networks

⚙️ WP-CLI framework

Feature Plugin to add SQLite support to WordPress. Under Development.

Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supportin…

A Native-PyTorch Library for LLM Fine-tuning

The official Meta Llama 3 GitHub site

Best Cron Docker Self-Hosted, Simple, lightweight, beautiful webui Cronjob / Scheduled task docker solution.

Stable and reliable WebHook, quickly connect to various systems. / 稳定靠谱的网络钩子，快速连接各种系统。

SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It solves 12.47% of bugs in the SWE-bench evaluation set and takes just 1 minute to run.

Benchmark LLMs by fighting in Street Fighter 3! The new way to evaluate the quality of an LLM

Implementation of "BitNet: Scaling 1-bit Transformers for Large Language Models" in pytorch

Grok open release

Pure go library for creating and processing Office Word (.docx), Excel (.xlsx) and Powerpoint (.pptx) documents

A tiny but valid `init` for containers

Minimal VirtIO drivers ISO

A Web Service Discovery host daemon.

QEMU in a Docker container.

GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection

Universal LLM Deployment Engine with ML Compilation

lightweight, standalone C++ inference engine for Google's Gemma models.

MiniCPM-2B: An end-side LLM outperforming Llama2-13B.

Tiny self-signed tool, file size between 1.5MB(binary) and 4MB (docker). Generate a self-hosted / dev certificate through configuration.