Mehdi Cherti (mehdidc)

mehdidc

Geek Repo

Company:Juelich Supercomputing Center (JSC), Forschungszentrum Jülich GmbH, LAION

Location:Germany

Home Page:https://mehdidc.github.io

Twitter:@mehdidc

Github PK Tool:Github PK Tool

Mehdi Cherti's starred repositories

magic-wormhole

get things from one computer to another, safely

Language:PythonLicense:MITStargazers:17773Issues:211Issues:329

PhotoMaker

PhotoMaker

Language:Jupyter NotebookLicense:NOASSERTIONStargazers:8051Issues:96Issues:114

surya

OCR, layout analysis, and line detection in 90+ languages

Language:PythonLicense:GPL-3.0Stargazers:5268Issues:60Issues:49
Language:PythonLicense:Apache-2.0Stargazers:3547Issues:44Issues:84

AlphaCodium

Official implementation for the paper: "Code Generation with AlphaCodium: From Prompt Engineering to Flow Engineering""

Language:PythonLicense:AGPL-3.0Stargazers:2922Issues:40Issues:13

StableVideo

[ICCV 2023] StableVideo: Text-driven Consistency-aware Diffusion Video Editing

Language:PythonLicense:Apache-2.0Stargazers:1315Issues:21Issues:22

self-rewarding-lm-pytorch

Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI

Language:PythonLicense:MITStargazers:1201Issues:23Issues:15

datatrove

Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.

Language:PythonLicense:Apache-2.0Stargazers:1068Issues:38Issues:40
Language:PythonLicense:Apache-2.0Stargazers:939Issues:10Issues:42

nanotron

Minimalistic large language model 3D-parallelism training

Language:PythonLicense:Apache-2.0Stargazers:693Issues:42Issues:38

ml-aim

This repository provides the code and model checkpoints of the research paper: Scalable Pre-training of Large Autoregressive Image Models

Language:PythonLicense:NOASSERTIONStargazers:600Issues:20Issues:3

taesd

Tiny AutoEncoder for Stable Diffusion

Language:PythonLicense:MITStargazers:378Issues:9Issues:12

Gemini

The open source implementation of Gemini, the model that will "eclipse ChatGPT" by Google

Language:PythonLicense:MITStargazers:342Issues:14Issues:5

Mask-Predict

A masked language modeling objective to train a model to predict any subset of the target words, conditioned on both the input text and a partially masked target translation.

Language:PythonLicense:NOASSERTIONStargazers:238Issues:7Issues:22
Language:PythonLicense:Apache-2.0Stargazers:232Issues:14Issues:16
Language:Jupyter NotebookLicense:MITStargazers:183Issues:7Issues:8

COMM

Pytorch code for paper From CLIP to DINO: Visual Encoders Shout in Multi-modal Large Language Models

tifa

TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering

Language:PythonLicense:Apache-2.0Stargazers:107Issues:4Issues:3

DynamicVectorQuantization

Official Pytorch Implementation of Our CVPR2023 Paper: "Towards Accurate Image Coding: Improved Autoregressive Image Generation with Dynamic Vector Quantization"

Language:PythonLicense:MITStargazers:105Issues:4Issues:8

Awesome-VQVAE

📚 A collection of resources and papers on Vector Quantized Variational Autoencoder (VQ-VAE) and its application

unitxt

🦄 Unitxt: a python library for getting data fired up and set for training and evaluation

Language:PythonLicense:Apache-2.0Stargazers:90Issues:10Issues:79

parallel-decoding

Repository of the paper "Accelerating Transformer Inference for Translation via Parallel Decoding"

Language:PythonLicense:Apache-2.0Stargazers:87Issues:3Issues:2

ocr-vqgan

OCR-VQGAN, a discrete image encoder (tokenizer and detokenizer) for figure images in Paper2Fig100k dataset. Implementation of OCR Perceptual loss for clear text-within-image generation. Fork from VQGAN in CompVis/taming-transformers

ENGINE

ENGINE: Energy-Based Inference Networks for Non-Autoregressive Machine Translation

Language:PythonLicense:NOASSERTIONStargazers:24Issues:3Issues:4

all-clip

Load any clip model with a standardized interface

Language:PythonLicense:MITStargazers:12Issues:0Issues:0

ACES

Audio Captioning Evaluation on Semantics of Sound (ACES)

Language:Jupyter NotebookLicense:MITStargazers:6Issues:1Issues:0

vqgan_nodep

VQGAN from LDM without hell of dependencies

Language:PythonStargazers:4Issues:1Issues:0

vq-compress

Image compression with pretrained latent diffusion autoencoding models.

Language:PythonLicense:Apache-2.0Stargazers:4Issues:2Issues:0
Language:PythonLicense:MITStargazers:2Issues:0Issues:0