User-friendly WebUI for LLMs (Formerly Ollama WebUI)

Robotic actuator test stand utilizing a Capstan Drive reducer

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

The uncompromising Python code formatter

Kolmogorov Arnold Networks

Finetune Llama 3, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

A collection of inspiring lists, manuals, cheatsheets, blogs, hacks, one-liners, cli/web tools and more.

Master programming by recreating your favorite technologies from scratch.

Chat Templates for 🤗 HuggingFace Large Language Models

Easier usage of LLMs in Rockchip's NPU on SBCs like Orange Pi 5 and Radxa Rock 5 series

Ubuntu 22.04 and 24.04 for Rockchip RK35XX Devices

Zero-Shot Speech Editing and Text-to-Speech in the Wild

SGLang is a structured generation language designed for large language models (LLMs). It makes your interaction with models faster and more controllable.

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

A benchmark for emotional intelligence in large language models

Simple, safe way to store and distribute tensors

Dataset indexer for blazing fast O(1) random access with virtually no memory overhead.

A library for making RepE control vectors

Convert PDF to markdown quickly with high accuracy

Meghna Hugo is a responsive, minimalist, lightweight, and fast loading one-page business theme built with HTML5/CSS3, Hugo, JavaScript, and JQuery.

Business Hugo template

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

The friendly PIL fork

A multimodal, function calling powered LLM webui.

Foundational model for human-like, expressive TTS

Self-hosted LLM chatbot arena, with yourself as the only judge

function calling-based LLM agents