lebrice

blurred-GAN

Progressive Growing of GANS using Gaussian Blur

Keras-Progressive-Growing-GANS

(WIP) My Attempt at a clean re-implementation of ["Progressive Growing of GANs for Improved Quality, Stability, and Variation"](https://github.com/tkarras/progressive_growing_of_gans) using the Keras API in TensorFlow. Contributions/Suggestions welcomed!

LLM_api

Testing out SLURM + FastAPI + HuggingFace

MeZO

[NeurIPS 2023] MeZO: Fine-Tuning Language Models with Just Forward Passes. https://arxiv.org/abs/2305.17333

pop-based-training

Simple Implementation of Enhanced Population Based Training for Loss Function Optimization [1](https://arxiv.org/abs/2002.04225) (I am not the author of this paper)

Sequoia

The Research Tree - A playground for research at the intersection of Continual, Reinforcement, and Self-Supervised Learning.

SimpleParsing

Simple, Elegant, Typed Argument Parsing with argparse

torch_jax_interop

Simple tools to mix and match PyTorch and Jax - Get the best of both worlds!

Tutorials

Source code for the Mila Tutorials

lebrice/SimpleParsing

Simple, Elegant, Typed Argument Parsing with argparse

lebrice/Sequoia

The Research Tree - A playground for research at the intersection of Continual, Reinforcement, and Self-Supervised Learning.

lebrice/torch_jax_interop

Simple tools to mix and match PyTorch and Jax - Get the best of both worlds!

lebrice/blurred-GAN

Progressive Growing of GANS using Gaussian Blur

lebrice/lebrice

lebrice/spatial

Fooling around, testing out the idea of making a Rust + Python version of gym.spaces. Not a serious project (_yet_ ?)

lebrice/torch-hook-utils

PyTorch Hook utilities

lebrice/MeZO

[NeurIPS 2023] MeZO: Fine-Tuning Language Models with Just Forward Passes. https://arxiv.org/abs/2305.17333

lebrice/compose

Simple, type-rich function composition in Python (this package contains a single `compose` function)

lebrice/demo_script

lebrice/gymnax

RL Environments in JAX 🌍

lebrice/hydra_orion_sweeper

Hydra Sweeper Plugin for Orion

lebrice/jax

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

lebrice/lightning-hydra-template

PyTorch Lightning + Hydra. A very user-friendly template for rapid and reproducible ML experimentation with best practices. ⚡🔥⚡

lebrice/mila-docs

Mila technical documentation

lebrice/milabench

Repository of training benchmarks

lebrice/milatools

Tools to connect to and interact with the Mila cluster

lebrice/mup

maximal update parametrization (µP)

lebrice/mup_orion_demo

Demo of mup for Orion

lebrice/optax

Optax is a gradient processing and optimization library for JAX.

lebrice/orion

Asynchronous Distributed Hyperparameter Optimization.

lebrice/petals

🌸 Run large language models at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading

lebrice/pytest-fixture-tools

Pytest fixture tools

lebrice/pytest-xdist

pytest plugin for distributed testing and loop-on-failures testing modes.

lebrice/replay-based-recurrent-rl

Code for "Task-Agnostic Continual RL: In Praise of a Simple Baseline"

lebrice/ResearchTemplate

WIP: Research Template Repository

lebrice/SARC

FD#11499

lebrice/tensor_regression

A small wrapper to use pytest_regressions with Tensors

lebrice/transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

lebrice/xtils

A collection of utilities for machine learning experiments.