Free and open-source map hosting solution with custom styles for websites and apps, using OpenStreetMap data

Felafax is building AI infra for non-NVIDIA GPUs

LLaMA-Omni is a low-latency and high-quality end-to-end speech interaction model built upon Llama-3.1-8B-Instruct, aiming to achieve speech capabilities at the GPT-4o level.

High-resolution maps in the browser, for printing

🦙 Integrating LLMs into structured NLP pipelines

Named Entity Recognition for Events & Temporal expressions

Implementation of "BitNet: Scaling 1-bit Transformers for Large Language Models" in pytorch

Mamba SSM architecture

An unofficial PyTorch implementation of the audio LM VALL-E

PyTorch implementation of VALL-E(Zero-Shot Text-To-Speech), Reproduced Demo https://lifeiteng.github.io/valle/index.html

This is the code for the SpeechTokenizer presented in the SpeechTokenizer: Unified Speech Tokenizer for Speech Language Models. Samples are presented on

Jupyter Notebook running Mamba speech synthesis example on Determined AI. Based on https://2084.substack.com/p/2084-marcrandbot-speech-synthesis

Implementation of Denoising Diffusion Probabilistic Model in Pytorch

[ICML 2024] Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model

Simple, minimal implementation of the Mamba SSM in one pytorch file. More efficient than using for loops, but probably less efficient than using associative scans

Experimental (working!) custom implementation of conditional and unconditional diffusion for testing new methods.

Collection of awesome LLM apps with RAG using OpenAI, Anthropic, Gemini and opensource models.

Programming Machine Learning - Elixir Livebooks

Self-contained, minimalistic implementation of diffusion models with Pytorch.

Deriving Machine Learning algorithms from first principles.

Tools designed for processing Pixel Art

Scripts to build a hiking-focused .pmtiles file and its stylesheets

A lightweight message queue. Like AWS SQS and RSMQ but on Postgres.

An unnecessarily tiny implementation of GPT-2 in NumPy.

The LoRA fine-tuning method implemented in Elixir

Inference and training library for high-quality TTS models.

The official Meta Llama 3 GitHub site

Almost-Pure Rust TTS Engine for my Rustnation talk

Instant voice cloning by MIT and MyShell.