-
rl Public
Forked from pytorch/rlA modular, primitive-first, python-first PyTorch library for Reinforcement Learning.
Python MIT License UpdatedOct 16, 2025 -
trackio Public
Forked from gradio-app/trackioA lightweight, local-first, and free experiment tracking library from Hugging Face 🤗
Python MIT License UpdatedOct 16, 2025 -
BenchMARL Public
Forked from facebookresearch/BenchMARLA collection of MARL benchmarks based on TorchRL
-
tdhook Public
🤖🪝Interpretability with tensordict and torch hooks.
-
football Public
Forked from google-research/footballOne more gfootball fork to fix the install
-
tensordict Public
Forked from pytorch/tensordictTensorDict is a pytorch dedicated tensor container.
Python MIT License UpdatedSep 8, 2025 -
lczerolens Public
🔬 Interpretability for Leela Chess Zero networks.
-
-
nnsight Public
Forked from ndif-team/nnsightThe nnsight package enables interpreting and manipulating the internals of deep learned models.
Jupyter Notebook MIT License UpdatedJul 30, 2025 -
-
v-lczero-bindings Public
Pypi export of lczero-bindings from https://github.com/LeelaChessZero/lc0.
-
marl-book-exercises Public archive
Forked from marl-book/marl-book-exercisesCode exercises for the MARL Textbook
Python UpdatedSep 18, 2024 -
vec_noise Public
Forked from zbenjamin/vec_noiseVectorized perlin noise library for Python
-
lczero-planning Public archive
Interpreting planning in LeelaChessZero networks.
-
mulsi Public archive
🔏 Safe inference using representation engineering.
-
-
-
mistral-playground Public archive
Simple playground wrapper around Mistral API.
Python MIT License UpdatedDec 13, 2023 -
ML-Engineer Public archive
Projects realised for the ML Engineer path on OpenClassrooms
-
AlgorithmDistillationInterpretability Public archive
Forked from ADInterpretabilityTeam/AlgorithmDistillationInterpretabilityInterpreting how transformers simulate reinforcement learning algorithms
Jupyter Notebook MIT License UpdatedJun 1, 2023 -
Iterative_summarization Public archive
Experiment on Iterative Summarisation, potentially linked to Natural Abstraction. Made for the Alignment jam #4.
Jupyter Notebook MIT License UpdatedJan 22, 2023 -
-
Logit_Lens Public archive
Reimplementation of the interpretability tool Logit Lens describe GPT-2 behaviour ([Lesswrong](https://www.lesswrong.com/posts/AcKRB8wDpdaN6v6ru/interpreting-gpt-the-logit-lens)).
UpdatedNov 6, 2022 -
Twitch_Analysis Public archive
Little study of the Twitch network from the point of vie of complex systems and graphs.
Jupyter Notebook Apache License 2.0 UpdatedJan 10, 2022 -
wgenpatex Public archive
Forked from ahoudard/wgenpatexWasserstein Generative Models for Patch-based Texture Synthesis
Python MIT License UpdatedJan 5, 2022 -
-
Ext_c_dcgan Public archive
Supplementary materials to my internship's report.
Python Other UpdatedDec 3, 2021 -
{{ message }}