- Lille, France
- linkedin.com/in/mmcenta/
- @mmcenta
Block or Report
Block or report mmcenta
Contact GitHub support about this user’s behavior. Learn more about reporting abuse.
Report abuseStars
Language
Sort by: Recently starred
Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step
Aim 💫 — An easy-to-use & supercharged open-source experiment tracker.
Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supportin…
Black-box extraction of Finite-State Machines from RNNs.
🕹️ A diverse suite of scalable reinforcement learning environments in JAX
a multi-task reinforcement learning environment compatible with OpenAI gym
Gin provides a lightweight configuration framework for Python
An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)
Google Research
Code for 'Dynamics-Aware Unsupervised Discovery of Skills' (DADS). Enables skill discovery without supervision, which can be combined with model-based control.
Working directory for dynamics learning for experimental robots.
Source code for the paper: "Neural Methods for Logical Reasoning over Knowledge Graphs"
Multi-Hop Logical Reasoning in Knowledge Graphs
Benchmarking the Spectrum of Agent Capabilities
ML Collections is a library of Python Collections designed for ML use cases.
Python bindings for FFmpeg - with complex filtering support
A simple and highly efficient RTS-game-inspired environment for reinforcement learning