godofnothing Goto Github PK
Name: Denis Kuznedelev
Type: User
Company: Skoltech
Location: Moscow, Russia
Name: Denis Kuznedelev
Type: User
Company: Skoltech
Location: Moscow, Russia
This is the Unsupervised Guidance For Semantic Segmentation. The aim of the project is to use the unsupervised segmentation as a prior of Neural Network model.
A framework for the evaluation of autoregressive code generation language models.
lm-evaluation-harness version with support of AQLM intermediate checkpoints
A Compressed Stable Diffusion for Efficient Text-to-Image Generation [ICCV'23 Demo] [ICML'23 Workshop]
Sparsification of Bloom
Repository for experiments with several approaches to fine-tune model, pretrained on the CLIP: https://openai.com/blog/clip/
Consistency Distilled Diff VAE
Repository for performing different experiments for different tasks in CV.
Deep Learning course materials (HSE, Faculty of Computer Science)
A fork of DL4AGX with support for timm models
Our implementation of the paper "Object Detection in Large Images"
Implementation of G-Conv from Cohen&Welling
Repository for anomaly detection on Tabular data with normalising flows.
Optuna tuning of hyperparams on Heterophily datasets.
Official code release for "GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis"
implementation of Graph2NN paper - https://arxiv.org/abs/2007.06559
NaN
The implementation of HMC single neuron based on MacKay's book
Training GNNs on heterophilous graphs.
Matplotlib animation of Hilbert curves
LLM sparse training code for MosaicML foundation models
Based on https://github.com/princeton-nlp/LM-Kernel-FT
Repository for the networks solving the majority problems in different settings.
FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens. Version with scale finetuning.
Jupyter notebooks for "A high-bias, low-variance introduction to Machine Learning for physicists"
OpenMMLab Detection Toolbox and Benchmark
Fast and Easy Infinite Neural Networks in Python
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.