Gökdeniz Gülmez

Local-NotebookLM. Googles NotebookLM but local

mlx-lm-lora. Train Large Language Models on MLX.

mlx-lm-lens. Find the hidden meaning of LLMs

mlx-kan. KAN (Kolmogorov–Arnold Networks) in the MLX framework for Apple Silicon

Mixtral-from-scratch-in-MLX. An implementation of Mistral.ai's Mixtral in Apples MLX Framework: Pre-train and Fine-tune Mixtral on your MacBook

mlx-examples. Examples in the MLX framework

J.O.S.I.E.-v4o. Python

vibe-coded-speech-to-speech. Almost Real-Time Speech-to-Speech System literally only Vibe Coded using my private Josiefied-Coder-32B model

mlx-lm. LLM text generation and fine-tuning with MLX

KANama. Llama3.1 x Kolmogorov–Arnold Networks

josie_dev. The Main Multimodal Model for real time interactions and Smart-Home-Management

mlx-audio. A text-to-speech (TTS) and Speech-to-Speech (STS) library built on Apple's MLX framework, providing efficient speech synthesis on Apple Silicon.

CL4R1T4S. SYSTEM PROMPT TRANSPARENCY FOR ALL - CHATGPT, GEMINI, GROK, CLAUDE, PERPLEXITY, CURSOR, WINDSURF, DEVIN, REPLIT, AND MORE!

OpenAudioAPI. This is a local API for TTS and STT using the latest Models and frameworks including MLX, in the OpenAI API format

My-Own-Smarthome-AI. That’s an AI that learns from your way of controlling the home, so that you don’t have to do anything.

deep-research. An AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models. The goal of this repo is to provide the simplest implementation of a deep research agent - e.g. an agent that can refine its research direction overtime and deep dive into a topic.

Goekdeniz-Guelmez. Finally, something to make my profile appealing.

Perplexica. Perplexica is an AI-powered search engine. It is an Open source alternative to Perplexity AI

Inside-Llama. Here we will go through all the inner workings of Meta's Llama model and architecture.

TinyZero. Clean, accessible reproduction of DeepSeek R1-Zero

TransformerLens. A library for mechanistic interpretability of GPT-style language models

smollm. Everything about the SmolLM2 and SmolVLM family of models

KANama-MLX. KANama in MLX

OpenWebUI-Pipelines. Just for my OpenWebUI usage

WLED-with-Homekit. C++