Frédéric Branchaud-Charron

open-r1. Fully open reproduction of DeepSeek-R1

nightline. Nightline is a modern Event Listening framework based on Pydantic.

transformers. 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

fundus. A very simple news crawler with a funny name

supervision. We write your reusable computer vision tools. 💜

WordLlama. Things you can do with the token embeddings of an LLM

AIEnergyScore. AI Energy Score: Initiative to establish comparable energy efficiency ratings for AI models.

easy_ViTPose. Easy and fast 2d human and animal multi pose estimation using SOTA ViTPose [Y. Xu et al., 2022] Real-time performances and multiple skeletons supported.

kharon. Simplify Secure App Sharing

ByteTrack. [ECCV 2022] ByteTrack: Multi-Object Tracking by Associating Every Detection Box

neural_net_checklist. Python

RustModel. Rust

torchchat. Run PyTorch LLMs locally on servers, desktop and mobile

flux. Official inference repo for FLUX.1 models

domain-matcher. Protect your models from out of scope domains. Focus on what matters.

Stirling-PDF. #1 PDF Application on GitHub that lets you edit PDFs on any device anywhere

commands. Commands - a React Hooks library for writing async code

text-embeddings-inference. A blazing fast inference solution for text embeddings models

bm25s. Fast BM25 search in Python, powered by Numpy and Numba

fastapi-dependency-tutorial. Real-life example of Dependency Injection using FastAPI

logfire. AI observability platform for production LLM and agent systems.

mkposters. Make posters from Markdown files.

outlines. Structured Outputs

full-stack-fastapi-template. Full stack, modern web application template. Using FastAPI, React, SQLModel, PostgreSQL, Docker, GitHub Actions, automatic HTTPS and more.

baal. Bayesian active learning library for research and industrial usecases.

arrest. Arrest is a small utility to easily structure and validate your REST api calls using pydantic and httpx

spaCy. 💫 Industrial-strength Natural Language Processing (NLP) in Python

FriendsDontLetFriends. Friends don't let friends make certain types of data visualization - What are they and why are they bad.

clipper.js. HTML to Markdown converter and crawler.

NLPretext. All the goto functions you need to handle NLP use-cases, integrated in NLPretext

harlequin. The SQL IDE for Your Terminal.

Adala. Adala: Autonomous DAta (Labeling) Agent framework

how-engineering-communicates. A community version of the "common API" for how the GitHub Engineering organization communicates

text-generation-inference. Large Language Model Text Generation Inference

azimuth. Helping AI practitioners better understand their datasets and models in text classification. From ServiceNow.

evidently. Evidently is ​​an open-source ML and LLM observability framework. Evaluate, test, and monitor any AI-powered system or data pipeline. From tabular data to Gen AI. 100+ metrics.

llm-numbers. Numbers every LLM developer should know

adept-augmentations. A Python library aimed at dissecting and augmenting NER training data.

textaugment. TextAugment: Text Augmentation Library

serge. A web interface for chatting with Alpaca through llama.cpp. Fully dockerized, with an easy to use API.

Text-Summarization. Abstractive and Extractive Text summarization using Transformers.

compromise. modest natural-language processing

BERTopic. Leveraging BERT and c-TF-IDF to create easily interpretable topics.

React-Jupyter-Viewer. A react component to embed .ipyb notebooks in a blog or something

TextDescriptives. A Python library for calculating a large variety of metrics from text

awesome-normconf. List of resources coming out of Normconf Slack

bert-extractive-summarization. MobileBERT and DistilBERT for extractive summarization

react-shopping-cart. Simple Shopping Cart using React Hooks, Context API and more.

pepy. pepy is a site to get statistics information about any Python package.

mkdocs-jupyter. Use Jupyter Notebook in mkdocs

react-shopping-cart. TypeScript

KeyBERT. Minimal keyword extraction with BERT

Styleformer. A Neural Language Style Transfer framework to transfer natural language text smoothly between fine-grained language styles like formal/casual, active/passive, and many more. Created by Prithiviraj Damodaran. Open to pull requests and other forms of collaboration.

energizer. An active learning library for Pytorch based on Lightning-Fabric.

stable-diffusion-videos. Create 🔥 videos with Stable Diffusion by exploring the latent space and morphing between text prompts

awesome-data-leadership. A curated list of awesome posts, videos, and articles on leading a data team (small and large)

chat_summarization_tutorial. Python

1-on-1s. 🌱 1-on-1 questions and resources from my time as a manager.

refinery. The data scientist's open-source choice to scale, assess and maintain natural language data. Treat training data like a software artifact.

gotop. A terminal based graphical activity monitor inspired by gtop and vtop

datasets_sql. Execute arbitrary SQL queries on 🤗 Datasets

TyXe. Jupyter Notebook

bert-extractive-summarizer. Easy to use extractive text summarization with BERT

react-transcript-editor. A React component to make correcting automated transcriptions of audio and video easier and faster. By BBC News Labs. - Work in progress

evaluate. 🤗 Evaluate: A library for easily evaluating machine learning models and datasets.

nflows. Normalizing flows in PyTorch

datasets. 🤗 The largest hub of ready-to-use datasets for AI models with fast, easy-to-use and efficient data manipulation tools

causal-bald. Python

coresets. Coresets

RustPython. A Python Interpreter written in Rust

blitz-bayesian-deep-learning. A simple and extensible library to create Bayesian Neural Network layers on PyTorch.

Emilian-Aryav-Repo. Python

Representer_Point_Selection. code release for Representer point Selection for Explaining Deep Neural Network in NeurIPS 2018

loss-surface-simplexes. Jupyter Notebook

ml-fairness-gym. Python

pytorch-revgrad. A minimal pytorch package implementing a gradient reversal layer.

robustness_metrics. Jupyter Notebook

XAI-papers.

austin-tui. The top-like text-based user interface for Austin

torchdatasets. PyTorch dataset extended with map, cache etc. (tensorflow.data like)

imodels. Interpretable ML package 🔍 for concise, transparent, and accurate predictive modeling (sklearn-compatible).

opensource.guide. 📚 Community guides for open source creators

active-bayesian-coresets. Python

stvae. Style transfer VAE package

swav. PyTorch implementation of SwAV https//arxiv.org/abs/2006.09882

synbols. The Synbols dataset generator is a ServiceNow Research project that was started at Element AI.

RoadDamageDetector. Jupyter Notebook

rows. A common, beautiful interface to tabular data, no matter the format

fairlearn. A Python package to assess and improve fairness of machine learning models.

last_layer_laplace. Last-layer Laplace approximation code examples

deterministic-uncertainty-quantification. Code for "Uncertainty Estimation Using a Single Deep Deterministic Neural Network"

LaplacianShot. Laplacian Regularized Few Shot Learning

byol-pytorch. Usable Implementation of "Bootstrap Your Own Latent" self-supervised learning, from Deepmind, in Pytorch

lightning-bolts. Toolbox of models, callbacks, and datasets for AI/ML researchers.

csgmcmc. Cyclical Stochastic Gradient MCMC for Bayesian Deep Learning

al-fk-self-supervision. Official PyTorch code for CVPR 2020 paper "Deep Active Learning for Biased Datasets via Fisher Kernel Self-Supervision"

constellation. Distributed programming for Rust.

incoherent-thoughts. Paradoxically, the notes are quite coherent.

pytorch-lightning. Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.

macchiato-dns. A simple DNS proxy server that that will protect your communications

HeteroscedasticDropoutUncertainty. Demos demonstrating the difference between homoscedastic and heteroscedastic regression with dropout uncertainty.

the-art-of-command-line. Master the command line, in one page

word_cloud. A little word cloud generator in Python

hask-trpg. Multiplayer Tactical RPG using Servant and Polysemy

gecco-tutorial-2019. 2019 talk at GECCO

AnchorFreeDetection. list the paper for recently anchor free detector

tsne-cuda. GPU Accelerated t-SNE for CUDA with Python bindings

governance. Governance of the Keras API.

io. Dataset, streaming, and file system extensions maintained by TensorFlow SIG-IO

mdx-deck. ♠️ React MDX-based presentation decks

tch-rs. Rust bindings for the C++ api of PyTorch.

mazelab. A customizable framework to create maze and gridworld environments

imagehash. A Python Perceptual Image Hashing Module

imagehash. A Python Perceptual Image Hashing Module

GP-Clustering. Clustering with Gaussian Process Models

gcn. Implementation of Graph Convolutional Networks in TensorFlow

textfsm. Python module for parsing semi-structured text into python tables.

Sublist3r. Fast subdomains enumeration tool for penetration testers

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

probabilistic_unet. A U-Net combined with a variational auto-encoder that is able to learn conditional distributions over semantic segmentations.

nvtop. GPU & Accelerator process monitoring for AMD, Apple, Huawei, Intel, NVIDIA and Qualcomm

starlette. The little ASGI framework that shines. 🌟

Neural-Style-Transfer-Papers. :pencil2: Neural Style Transfer: A Review

pushbullet-cli. Access Pushbullet from the command line

masonite. The Modern And Developer Centric Python Web Framework. Be sure to read the documentation and join the Discord channel for questions: https://discord.gg/TwKeFahmPZ

large-scale-curiosity. Code for the paper "Large-Scale Study of Curiosity-Driven Learning"

DeepSpectralClustering. Pytorch Implemention of paper "Deep Spectral Clustering Learning", the state of the art of the Deep Metric Learning Paper

tf-nlp-blocks. Some frequently used NLP blocks I implemented

NeuralTuringMachine. Tensorflow implementation of a Neural Turing Machine

lagom. lagom: A PyTorch infrastructure for rapid prototyping of reinforcement learning algorithms.

Switchable-Normalization. Code for Switchable Normalization from "Differentiable Learning-to-Normalize via Switchable Normalization", https://arxiv.org/abs/1806.10779

GAN_stability. Code for paper "Which Training Methods for GANs do actually Converge? (ICML 2018)"

Few-Shot-Music-Generation. Python

RelativisticGAN. Code for replication of the paper "The relativistic discriminator: a key element missing from standard GAN"

fastai. The fastai deep learning library

retro. Retro Games in Gym

WorldModelsExperiments. World Models Experiments

NLP-progress. Repository to track the progress in Natural Language Processing (NLP), including the datasets and the current state-of-the-art for the most common NLP tasks.

pytorch_geometric. Graph Neural Network Library for PyTorch

fairseq. Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

torchcv. TorchCV: a PyTorch vision library mimics ChainerCV

keras-applications. Reference implementations of popular deep learning models.

keras-preprocessing. Utilities for working with image data, text data, and sequence data.

checkered-cnn. A new technique to increase receptive field in convolutional neural networks without losing so much information.

dzen2-calendar. Ruby

elm-mdl-dashboard. elm-mdl-dashboard Example

bit. AI-powered development workspaces with reusable components, architectural clarity and zero overhead.

HaskTorrent. Haskell

gamemode. Optimise Linux system performance on demand

icecream. 🍦 Never use print() to debug again.

Multicore-TSNE. Parallel t-SNE implementation with Python and Torch wrappers.

Keras-GAN. Keras implementations of Generative Adversarial Networks.

git-flight-rules. Flight rules for git

tangent. Source-to-Source Debuggable Derivatives in Pure Python

pybib. Get BibTeX citations from your terminal

TCN. Sequence modeling benchmarks and temporal convolutional networks

ML-LaTeX-Shortcuts. A collection of LaTeX shortcuts for commonly used mathematical expressions in machine learning.

dlbook_notation. LaTeX files for the Deep Learning book notation

antinex-datasets. Datasets for training deep neural networks to defend software applications

msvag. TensorFlow implementation of (Momentum) Stochastic Variance-Adapted Gradient.

TerpreT. Python

obfuscated-gradients. Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples

Terminal.Gui. Cross Platform Terminal UI toolkit for .NET

Chatistics. 💬 Python scripts to parse Messenger, Hangouts, WhatsApp and Telegram chat logs into DataFrames.

flownet2-pytorch. Pytorch implementation of FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks

profile-summary-for-github. Tool for visualizing GitHub profiles

visual-attention. Python

magenta. Magenta: Music and Art Generation with Machine Intelligence

CapsNet-Keras. A Keras implementation of CapsNet in NIPS2017 paper "Dynamic Routing Between Capsules". Now test error ＝ 0.34%.

Mask_RCNN. Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow

hfnn. Haskell

StackGAN-v2. Python

inline-c. Haskell

SparseConvNet. Submanifold sparse convolutional networks

UNIT. Unsupervised Image-to-Image Translation

EAST. A tensorflow implementation of EAST text detector

seq2seq-chatbot. Chatbot in 200 lines of code using TensorLayer

keras-transform. Library for data augmentation

rec-attend-public. Code that implements paper "End-to-End Instance Segmentation with Recurrent Attention"

cityscapesScripts. README and scripts for the Cityscapes Dataset

arc-pytorch. The first public PyTorch implementation of Attentive Recurrent Comparators

Harambot. Download all the data from a group conversation on messenger

revnet-public. Code for "The Reversible Residual Network: Backpropagation Without Storing Activations"

umap. Uniform Manifold Approximation and Projection

TwiolioRN. A react native SMS client based on twilio

siamfc-tf. SiamFC tracking in TensorFlow.

SNNs. Tutorials and implementations for "Self-normalizing networks"

infiniteboost. InfiniteBoost: building infinite ensembles with gradient descent

deep_complex_networks. Implementation related to the Deep Complex Networks

NLDF. Python

noreward-rl. [ICML 2017] TensorFlow code for Curiosity-driven Exploration for Deep Reinforcement Learning

subpixel. subpixel: A subpixel convnet for super resolution with Tensorflow

edward. A probabilistic programming language in TensorFlow. Deep generative models, variational inference.

FC-DenseNet. Fully Convolutional DenseNets for semantic segmentation.

tensorflow. An Open Source Machine Learning Framework for Everyone

tf_unet. Generic U-Net Tensorflow implementation for image segmentation

reinforcement-learning. Minimal and Clean Reinforcement Learning Examples

dnc. A TensorFlow implementation of the Differentiable Neural Computer.

One-Hundred-Layers-Tiramisu. Keras Implementation of The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation by (Simon Jégou, Michal Drozdzal, David Vazquez, Adriana Romero, Yoshua Bengio)

FastMaskRCNN. Mask RCNN in TensorFlow