Clément

pytorch-scarf. Implementation of SCARF: Self-Supervised Contrastive Learning using Random Feature Corruption in Pytorch, a model learning a representation of tabular data using contrastive learning. It is inspired from SimCLR and uses a similar architecture and loss.

wukong-recommendation. Implements the paper "Wukong: Towards a Scaling Law for Large-Scale Recommendation" from Meta.

scratch-llm. From-scratch Llama 2-inspired Transformer in PyTorch for exploring tokenization, pre-training, and inference.

evidential-deeplearning. Implementation of "Evidential Deep Learning to Quantify Classification Uncertainty" proposing a method to quantify uncertainty in a neural network.

multitask-learning. Tensorflow implementation of three architectures for multi-task learning, a paradigm to learn different prediction tasks jointly using one model

ctr-prediction. Implementation of some state-of-the-art deep learning architectures for CTR prediction tasks, both in Pytorch and Tensorflow

portfolio-balance. Streamlit application to optimally re-balance a portfolio given a target allocation, current positions and market prices

ecommerce-dash. Example of a Dash application applied to e-commerce data to represent key metrics in the form of an interactive dashboard

final-mlp. Implements SOTA architecture for CTR predictions tasks, both in Pytorch and Tensorflow

parqstream. High-performance Parquet dataloader for ML pipelines with multithreaded prefetching to keep GPU busy.

rust-graph. Small graph library in rust for fun.

fastapi-fraud-detection. Example of a fully packaged ML model in a Docker image and exposed as a REST API using FastAPI framework

ssl-images. Implements VICReg, NT-Xent and DCL losses for contrastive self-supervised learning to generate semantically meaningful representations of images without labels.

rust-hnsw. Rust implementation of HNSW for approximate nearest-neighbor search, generic over distance metrics and vector types.

jax-bandits. Epsilon-greedy, UCB and Thomson sampling for Bernoulli rewards in pure jitted Jax

rust-bandits. Real-time Rust experimentation platform with UCB and Thompson Sampling bandits, persistent state, and recovery.

polars-plugins. Demonstrates how to implement custom expression in rust for polars and use them in python