Yoann Poupart's repositories
lczerolens
🔬 Interpretability for Leela Chess Zero networks.
lczero-planning
Interpreting planning in LeelaChessZero networks.
ML-Engineer
Projects realised for the ML Engineer path on OpenClassrooms
mistral-playground
Simple playground wrapper around Mistral API.
AlgorithmDistillationInterpretability
Interpreting how transformers simulate reinforcement learning algorithms
Ext_c_dcgan
Supplementary materials to my internship's report.
gradio
Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!
hugginglens
TransformerLens + HuggingFace
Iterative_summarization
Experiment on Iterative Summarisation, potentially linked to Natural Abstraction. Made for the Alignment jam #4.
jsonformer
A Bulletproof Way to Generate Structured JSON from Language Models
Logit_Lens
Reimplementation of the interpretability tool Logit Lens describe GPT-2 behaviour ([Lesswrong](https://www.lesswrong.com/posts/AcKRB8wDpdaN6v6ru/interpreting-gpt-the-logit-lens)).
ronrhone
Application de gestion pour l'association ronrhone
scrapy-selenium
Scrapy middleware to handle javascript pages using selenium
transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
Twitch_Analysis
Little study of the Twitch network from the point of vie of complex systems and graphs.
wgenpatex
Wasserstein Generative Models for Patch-based Texture Synthesis
zennit
Zennit is a high-level framework in Python using PyTorch for explaining/exploring neural networks using attribution methods like LRP.
zennit-crp
An eXplainable AI toolkit with Concept Relevance Propagation and Relevance Maximization