Skip to content
View gabriel-mercier's full-sized avatar

Highlights

  • Pro

Block or report gabriel-mercier

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
gabriel-mercier/README.md

Hi, I'm Gabriel Mercier

An Applied Maths and Machine/Deep Learning student from Paris

Coding

Connect with me:

gabriel-mercier-5b2536268 gabriel mercierx leetgab22

Languages and Tools:

arduino cplusplus grafana java pandas python pytorch scikit_learn tensorflow

Pinned Loading

  1. AI-LLM-Driven-NPC-Generation-A-Virtual-Village-Simulation AI-LLM-Driven-NPC-Generation-A-Virtual-Village-Simulation Public

    This project explores the use of artificial intelligence to generate realistic non-player characters (NPCs) in a virtual village environment. The NPCs are designed to interact autonomously, creatin…

    Python 16

  2. Hierarchical-Federated-Learning-to-Forecast-Soil-Water-Levels Hierarchical-Federated-Learning-to-Forecast-Soil-Water-Levels Public

    This project involves the development and optimization of an LSTM model for 5-hour forecasts on real agricultural time series (2000-3000 entries). The model is integrated into a custom-made Hierarc…

    Jupyter Notebook 1 1

  3. Kaggle-Winning-Project-Forest-Type-Classification Kaggle-Winning-Project-Forest-Type-Classification Public

    This project aims to classify forest cover types using environmental and spatial features. It was developed as part of Polytechnique APM 51053 EP course and demonstrates end-to-end ML workflow impl…

    Jupyter Notebook 1 1

  4. Small-Langage-Model-Finetuning-for-Summarization Small-Langage-Model-Finetuning-for-Summarization Public

    Pipeline to generate a French summarization dataset with Qwen2.5-32B-Instruct, then fine-tune lightweight models (T5-base, mT5-base, Qwen-0.5B) using LoRA (4-bit quantization, r = 8–128). We compar…

    Jupyter Notebook

  5. Deep-RL-Agents-for-Cathedral-Board-Game Deep-RL-Agents-for-Cathedral-Board-Game Public

    Deep RL agents for the Cathedral board game: self-play DQN & PPO, plus curriculum and representation learning experiments.

    Jupyter Notebook

  6. DevZoneX/face-to-emojis DevZoneX/face-to-emojis Public

    Jupyter Notebook 1