#
jmribeiro
Follow
Starred repositories
High performance AI inference stack. Built for production. @ziglang / @openxla / MLIR / @bazelbuild
LeanRL is a fork of CleanRL, where selected PyTorch scripts optimized for performance using compile and cudagraphs.
A multi-platform desktop application to evaluate and compare LLM models, written in Rust and React.
A playbook for systematically maximizing the performance of deep learning models.
🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support
16-fold memory access reduction with nearly no loss
Clean PyTorch implementations of imitation and reward learning algorithms
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
Offline Reinforcement Learning (aka Batch Reinforcement Learning) on Atari 2600 games
FinRL: Financial Reinforcement Learning. 🔥
Get up and running with Llama 3.2, Mistral, Gemma 2, and other large language models.
[AAMAS 2023] Code for the paper "Automatic Noise Filtering with Dynamic Sparse Training in Deep Reinforcement Learning"
Paper code for Multi-task learning without Catastrophic Forgetting in Deep Reinforcement Learning (https://login.easychair.org/publications/paper/8RPq)
The original sources of MS-DOS 1.25, 2.0, and 4.0 for reference purposes
A collection of MARL benchmarks based on TorchRL
🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning
This project is a speech recognition system that converts speech into text using Python as the main language. It then uses a Language Model (LM) to generate responses based on user requests. The pr…
A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.
RL starter files in order to immediately train, visualize and evaluate an agent without writing any line of code
Graph Neural Network Library for PyTorch
Python package built to ease deep learning on graph, on top of existing DL frameworks.
Simple and easily configurable grid world environments for reinforcement learning
Train transformer language models with reinforcement learning.
A free and strong UCI chess engine
