Pinned Repositories
01
The open-source language model computer
ai-clone-whatsapp
Create an AI clone of yourself from your WhatsApp chats (using Mistral 7B)
AI-Inception
ai-lab-recipes
Examples for building and running LLM services and applications locally with Podman
ai-renamer
A Node.js CLI tool that uses Ollama models (Llama, Gemma, Phi etc.) to intelligently rename files in a specified directory
alma
Create Arch Linux based bootable USB drives
asteroids-genetic
Interactive AI training simuation
Bend
A massively parallel, high-level programming language
bend-mlp
A simple MLP written in the recently released Bend programming language.
bootlib
A minimalistic library to help making your x86 assembly program bootable.
lordunix's Repositories
lordunix/01
The open-source language model computer
lordunix/ai-clone-whatsapp
Create an AI clone of yourself from your WhatsApp chats (using Mistral 7B)
lordunix/AI-Inception
lordunix/ai-lab-recipes
Examples for building and running LLM services and applications locally with Podman
lordunix/ai-renamer
A Node.js CLI tool that uses Ollama models (Llama, Gemma, Phi etc.) to intelligently rename files in a specified directory
lordunix/alma
Create Arch Linux based bootable USB drives
lordunix/Bend
A massively parallel, high-level programming language
lordunix/bend-mlp
A simple MLP written in the recently released Bend programming language.
lordunix/Box64Droid
Running x86_64 applications on Android
lordunix/chatgpt-voice
Have a conversation with ChatGPT. Casually 🔈 🤖 ⚡️
lordunix/diffusers-rs
An implementation of the diffusers api in Rust
lordunix/Fomos
Experimental OS, built with rust
lordunix/llama2.c
Llama 2 Everywhere (L2E)
lordunix/StableDiffusion
Inference Stable Diffusion with C# and ONNX Runtime
lordunix/fabric
fabric is an open-source framework for augmenting humans using AI. It provides a modular framework for solving specific problems using a crowdsourced set of AI prompts that can be used anywhere.
lordunix/kalilinux-docker
Kali Linux on browser (Docker)
lordunix/llama3.cuda
llama3.cuda is a pure C/CUDA implementation for Llama 3 model.
lordunix/llama3.np
llama3.np is a pure NumPy implementation for Llama 3 model.
lordunix/llmware
Unified framework for building enterprise RAG pipelines with small, specialized models
lordunix/mistral.rs
Blazingly fast LLM inference.
lordunix/open-interpreter
A natural language interface for computers
lordunix/Open-Sora
Open-Sora: Democratizing Efficient Video Production for All
lordunix/PowerInfer
High-speed Large Language Model Serving on PCs with Consumer-grade GPUs
lordunix/RealtimeSTT
A robust, efficient, low-latency speech-to-text library with advanced voice activity detection, wake word activation and instant transcription.
lordunix/RealtimeTTS
Converts text to speech in realtime
lordunix/Rerender_A_Video
Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation
lordunix/screen-pipe
Record your screen & mic 24/7 and connect it to LLMs. Inspired by adept.ai, rewind.ai, Apple Shortcut. Written in Rust. Free. You own your data.
lordunix/TinyLlama
The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.
lordunix/tree-diffusion
lordunix/wolverine