Antoine Théberge's starred repositories
copilot.vim
Neovim plugin for GitHub Copilot
SelfMedMAE
Code for ISBI 2023 paper "Self Pre-training with Masked Autoencoders for Medical Image Classification and Segmentation"
CrossQ-Pytorch
CrossQ implementation in Pytorch
llama3-from-scratch
llama3 implementation one matrix multiplication at a time
XTRACT_atlases
WM tract atlases for the human (HCP and UK Biobank) and Macaque brain and connectivity blueprint atlases for the human (HCP) and macaque brain.
clean-rl-mlx
Clean RL implementation using MLX
PRML-Solution-Manual
My Own Solution Manual of PRML
softlearning
Softlearning is a reinforcement learning framework for training maximum entropy policies in continuous domains. Includes the official implementation of the Soft Actor-Critic algorithm.
torch-harmonics
Differentiable spherical harmonic transforms and spherical convolutions in PyTorch
EfficientZero
Open-source codebase for EfficientZero, from "Mastering Atari Games with Limited Data" at NeurIPS 2021.
Recurrent-Deep-Q-Learning
Solving POMDP using Recurrent networks
DRLearner_beta
Open Source Deep Reinforcement Learning, based on Agent 57 (Badia et al, 2020)
rainbow-is-all-you-need
Rainbow is all you need! A step-by-step tutorial from DQN to Rainbow
RWKV-LM
RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.