ggerganov

ggerganov's Stars

• karpathy/llm.c

  LLM training in simple, raw C/CUDA

  Language:Cuda24.9k2521412.8k

• karpathy/minbpe

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

  Language:Python9.3k8538877

• google/magika

  Detect file content types with deep learning

  Language:Rust8.3k38447428

• reorproject/reor

  Private & local AI personal knowledge management app for high entropy people.

  Language:TypeScript7.4k48203456

• google/gemma.cpp

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

  Language:C++6.1k4188520

• nilsherzig/LLocalSearch

  LLocalSearch is a completely locally running search aggregator using LLM Agents. The user can ask a question and the system will use a chain of LLMs to find the answer. The user can see the progress of the agents and the final answer. No OpenAI or Google API keys are needed.

  Language:Go5.7k3097365

• alexpinel/Dot

  Text-To-Speech, RAG, and LLMs. All local!

  Language:JavaScript1.7k2115102

• huggingface/huggingface.js

  Utilities to use the Hugging Face Hub API

  Language:TypeScript1.5k48290254

• yusufcanb/tlm

  Local CLI Copilot, powered by CodeLLaMa. 💻🦙

  Language:Go1.3k111740

• intel/openvino-plugins-ai-audacity

  A set of AI-enabled effects, generators, and analyzers for Audacity®.

  Language:C++1.1k2927471

• nkasmanoff/pi-card

  Raspberry Pi Voice Assistant

  Language:Python752141034

• distantmagic/paddler

  Stateful load balancer custom-tailored for llama.cpp 🏓🦙

  Language:Rust66081627

• abgulati/LARS

  An application for running LLMs locally on your device, with your documents, facilitating detailed citations in generated responses.

  Language:Python516102340

• ngxson/wllama

  WebAssembly binding for llama.cpp - Enabling on-browser LLM inference

  Language:C++47857827

• EtherDream/headphone-morse-transmitter

  Send Morse code via ⏮️ ⏸️ ⏯️

  Language:HTML4092021

• AndrewVeee/nucleo-ai

  An AI assistant beyond the chat box.

  Language:HTML31792029

• Daivuk/PureDOOM

  Pure DOOM - Single Header Doom Source Port

  Language:C++3074927

• AlexBuz/llama-zip

  LLM-powered lossless compression tool

  Language:Python25861910

• tangledgroup/llama-cpp-wasm

  WebAssembly (Wasm) Build and Bindings for llama.cpp

  Language:JavaScript22341217

• edgenai/llama_cpp-rs

  High-level, optionally asynchronous Rust bindings to llama.cpp

  Language:Rust19153137

• futo-org/whisper-acft

  Language:Jupyter Notebook10311105

• fairydreaming/farel-bench

  Testing LLM reasoning abilities with family relationship quizzes.

  Language:Python50401

• AIWintermuteAI/whispercpp

  Pybind11 bindings for Whisper.cpp

  Language:C++48439

• ahoylabs/gguf.js

  A Javascript library (with Typescript types) to parse metadata of GGML based GGUF files.

  Language:TypeScript44211

• distantmagic/structured

  Extracts structured data from unstructured input. Programming language agnostic. Uses llama.cpp

  Language:Go43101

• okuvshynov/llama_duo

  asynchronous/distributed speculative evaluation for llama3

  Language:C++37210

• hyparam/hyllama

  llama.cpp gguf file parser for javascript

  Language:JavaScript30322

• Artefact2/llm-eval

  A super simple web interface to perform blind tests on LLM outputs.

  Language:PHP27103

• Mihaiii/trivia

  A live multiplayer trivia game where users can bid for the subject of the next question

  Language:Python22203

• astrowonk/emoji_finder

  emoji_finder

  Language:Python15422