Inference code for Llama models

Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable…

An uroboros program with 100+ programming languages

Convolutional Neural Networks

QLoRA: Efficient Finetuning of Quantized LLMs

AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head

Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.

🔊 Text-Prompted Generative Audio Model

Inpaint anything using Segment Anything and inpainting models.

LLM inference in C/C++

Code to accompany "A Method for Animating Children's Drawings of the Human Figure"

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

Scene Text Recognition with Permuted Autoregressive Sequence Models (ECCV 2022)

A packaged and flexible version of the CRAFT text detector and Keras CRNN recognition model.

This repository contains multiple C++/GPU version of a pipeline for object detection. This project has been done for a GPU class at EPITA.

Satellite imagery treatment pipeline : band combination, pansharpening & mosaicing.

Le docker français 🐳 🇫🇷

A cross-platform C and C++ unit testing framework for the 21st century

Quickly coded discord bot used to generate custom channels

An easy-to-use vlang module to parse OpenApi3 files

Medieval city map random generator

API client for the French forecast agency Météo France. Collects most recent forecast previsions on given points.

work related to EPITA teaching

Datasets pour les ateliers hub

Repository of the FTML Epita course.

Epita S2 Project. Epicoin is a blockchain system where the proof of work is replaced by the solving of NP-Complete problems.