artificial-intelligence

This repository is used to collect papers and code in the field of AI.

Transcription and TTS Rest API (OpenAI Whisper, Speechbrain)

A high performance C++ SDK for AI Agents

Implementation of Zorro, Masked Multimodal Transformer, in Pytorch

Fine-tuning of diffusion models

Python client library for improving your LLM app accuracy

Kyros — The Memory OS for AI Agents Give your AI agents secure, self-correcting, persistent memory in 3 lines of code. Three memory types (episodic, semantic, procedural) with built-in forgetting curves, cryptographic integrity, and automatic contradiction resolution. Model-agnostic REST API with Python and TypeScript SDKs.

A minimal TensorFlow.js re-implementation of Karpathy's minGPT (Generative Pre-trained Transformer). The GPT model itself is <300 lines of code.

Democratization of "PaLI: A Jointly-Scaled Multilingual Language-Image Model"

Dual Diffusion is a generative diffusion model for music trained on video game soundtracks.

Implementation of the transformer proposed in "Building Blocks for a Complex-Valued Transformer Architecture"

Implementation of 🌻 Mirasol, SOTA Multimodal Autoregressive model out of Google Deepmind, in Pytorch

Access to Sulie foundation models for time-series forecasting 📈

Absolutely amazing SOTA Google Colab (Jupyter) Notebooks for creating/training SOTA Music AI models and for generating music with Transformer technology (Google XLNet/Transformer-XL)

Pytorch code for ICRA'21 paper: "Hierarchical Cross-Modal Agent for Robotics Vision-and-Language Navigation"

Awesome LLM application repo

An autonomous, context-aware AI desktop companion. Built with Python, featuring real-time screen vision, custom ONNX voice synthesis, active window tracking, and a dynamic floating UI with reactive facial expressions.

A repository with exploration into using transformers to predict DNA ↔ transcription factor binding

Implementation of Perceiver, General Perception with Iterative Attention

Standalone Product Key Memory module in Pytorch - for augmenting Transformer models