🤗 Benchmark Large Language Models Reliably On Your Data

A fast AI Video Generator for the GPU Poor. Supports Wan 2.1/2.2, Qwen Image, Hunyuan Video, LTX Video and Flux.

Cross-platform advanced subtitle editor, with new feature branches. Read the README on the feature branch.

A faithful clone of Karpathy's llama2.c (one file inference, zero dependency) but fully functional with LLaMA 3 8B base and instruct models.

A fork of llama3.c used to do some R&D on inferencing

📬 Simple, private file sharing. Mirror of https://gitlab.com/timvisee/send

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

API server for Instant voice cloning by MyShell.

🖼️ A command-line system information tool written in bash 3.2+

NVIDIA Linux open GPU with P2P support

🔥 Ultra-fast in-memory static file server for SPAs and static content

Web tool for database management

Llama 2 Everywhere (L2E)

Inference Llama 2 in one file of pure Rust 🦀

Lightweight package for interacting with ChatGPT's API by OpenAI. Uses reverse engineered official API.

A discord bot that roleplays!

Optimized Stable Diffusion modified to run on lower GPU VRAM

Stable Diffusion web UI

Run GGUF models easily with a KoboldAI UI. One File. Zero Install.

DeepSpeed is a deep learning optimization library that makes distributed training easy, efficient, and effective.

Qemu.js source code with proof-of-concept machine-code-to-WASM JIT.

An Expert System designed to classify a variety of cheeses. Implemented in CLIPS

This is a medical diagnosis system programmed using CLIPS.

Expert System project for my undergraduate class: Knowledge Systems. Starring: NASA's CLIPS

A SQLite extension which loads a Google Sheet as a virtual table.

Inference on CPU code for LLaMA models

Fork of Facebooks LLaMa model to run on CPU

Emscripten-Port of Wolfenstein 3D and Spear of Destiny