The n-gram Language Model

AI wearable necklace

The memory layer for Personalized AI

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

Universal LLM Deployment Engine with ML Compilation

A high-level Python library for Quantum Natural Language Processing

Source code for the TKET quantum compiler, Python bindings and utilities

RL research on Android devices.

This repository contains code and configuration files for an Extract, Transform, Load (ETL) project using Google Cloud Data Fusion for data extraction, Apache Airflow/Composer for orchestration, an…

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

Secure and fast microVMs for serverless computing.

A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.

Mastering Diverse Domains through World Models

FinRL: Financial Reinforcement Learning. 🔥

Dropbear Humanoid Robot - an advanced humanoid robot designed to operate in varied environments, showcasing agility, precision, and intelligence.

Modular reinforcement learning library (on PyTorch and JAX) with support for NVIDIA Isaac Gym, Omniverse Isaac Gym and Isaac Lab

PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

Unified Reinforcement Learning Framework

Master programming by recreating your favorite technologies from scratch.

Efficient approach to speaker diarization using voice characteristics extraction

Command Your World with Voice

🤖 Build AI applications with confidence ✅ DSPy Visualizer ✅ Understand how your users are using your LLM-app ✅ Get a full picture of the quality performance of your LLM-app ✅ Collaborate with your …

Call all LLM APIs using the OpenAI format. Use Bedrock, Azure, OpenAI, Cohere, Anthropic, Ollama, Sagemaker, HuggingFace, Replicate (100+ LLMs)

Beautifully designed components that you can copy and paste into your apps. Accessible. Customizable. Open Source.

Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation

Multilingual and Controllable Text-to-Speech Toolkit of the Speech and Language Technologies Group at the University of Stuttgart.

A framework for serving and evaluating LLM routers - save LLM costs without compromising quality!