ggerganov

refined-github

:octocat: Browser extension that simplifies the GitHub interface and adds useful features

LLaVA

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

mlx

MLX: An array framework for Apple silicon

llamafile

Distribute and run LLMs with a single file.

seamless_communication

Foundational Models for State-of-the-Art Speech and Text Translation

sshx

Fast, collaborative live terminal sharing over the web

gpt-fast

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

localpilot

magentic

Seamlessly integrate LLMs as Python functions

swiss_army_llama

A FastAPI service for semantic text search using precomputed embeddings and advanced similarity measures, with built-in support for various file types through textract.

LLMFarm

llama and other large language models on iOS and MacOS offline using GGML library.

qwen.cpp

C++ implementation of Qwen-LM

llavavision

A simple "Be My Eyes" web app with a llama.cpp/llava backend

prompt-lookup-decoding

octogen

Octogen is an Open-Source Code Interpreter Agent Framework

LLM.swift

LLM.swift is a simple, and readable library which lets you locally interact with LLMs with ease for macOS, iOS, visionOS, watchOS, and tvOS.

ggml-k8s

Run GGML models with Kubernetes.

devresume

A free web-based resume editor based on writing YAML with realtime preview and PDF export.

vit.cpp

Inference Vision Transformer (ViT) in plain C/C++ with ggml

llava-cpp-server

LLaVA server (llama.cpp).

gbnfgen

TypeScript generator for llama.cpp Grammar directly from TypeScript interfaces

M5HamRadio

M5HamRadio Firmwares

fft

A collection of Fast Fourier Transform algorithms implemented in C++20.

llama-journey

Experimental adventure game with AI-generated content

shanocast

Google Chromecast Reciever

SpeziLLM

A module enabling the integration of Large Language Models (LLMs) with the Spezi Ecosystem

vision-core-ai

Demo python script app to interact with llama.cpp server using whisper API, microphone and webcam devices.

bunny-llama

iterate quickly with llama.cpp hot reloading. use the llama.cpp bindings with bun.sh

json-schema-to-gbnf

Converts JSON-Schema to GBNF grammar to use with llama.cpp

grammar-builder

Generates grammer files from typescript for LLM generation