[NeurIPS 2021] [T-PAMI] DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification

Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.

Library for industrial alignment.

[NeurIPS 2024 Best Paper][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ult…

🦖 X—LLM: Cutting Edge & Easy LLM Finetuning

Design Pattern Examples in Python

🧀 Code and models for the ICML 2023 paper "Grounding Language Models to Images for Multimodal Inputs and Outputs".

Running large language models on a single GPU for throughput-oriented scenarios.

Single-document unsupervised keyword extraction

High-quality single-file implementations of SOTA Offline and Offline-to-Online RL algorithms: AWAC, BC, CQL, DT, EDAC, IQL, SAC-N, TD3+BC, LB-SAC, SPOT, Cal-QL, ReBRAC

Word sense induction (WSI) dataset for Russian

Preprocessing of the dataset of 347 subtitles for the TV series (thanks to Taiga Corpus) to build a word2vec model, JamSpell model, neural network training, chat bot training or in any other NLP task.

Simple Python package for breaking Russian words into syllables

Pipeline for easy fine-tuning of BERT architecture for sequence classification

Материалы курса по компьютерной лингвистике Школы Лингвистики НИУ ВШЭ

Tools for shrinking fastText models (in gensim format)

Курс по машинному обучению для магистров компьютерной лингвистики 1-го курса в Высшей Школе Экономики

LEFTJOIN.ru public repository