379K subscribers
4.38K photos
835 videos
17 files
4.86K links
Погружаемся в машинное обучение и Data Science

Показываем как запускать любые LLm на пальцах.

По всем вопросам - @haarrp

@itchannels_telegram -🔥best channels

Реестр РКН: clck.ru/3Fmqri
Download Telegram
🦾 Robustness Gym is a Python evaluation toolkit for natural language processing.

Github: https://github.com/robustness-gym/robustness-gym

Paper: https://arxiv.org/abs/2101.04840v1

Project: https://robustnessgym.com/

@ai_machinelearning_big_data
Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet, arxiv

Github: https://github.com/yitu-opensource/T2T-ViT

Paper: https://arxiv.org/abs/2101.11986

ImageNet training: https://github.com/pytorch/examples/tree/master/imagenet

@ai_machinelearning_big_data
WeNet open source, production first and production ready end-to-end (E2E) speech recognition toolkit

Github: https://github.com/mobvoi/wenet

Paper: https://arxiv.org/abs/2102.01547v1

Tutorial: https://github.com/mobvoi/wenet/blob/main/docs/tutorial.md

@ai_machinelearning_big_data
Knover allows researchers and developers efficient training/inference of large-scale dialogue generation models.

Github: https://github.com/PaddlePaddle/Knover

Paper: https://arxiv.org/abs/2102.02096v1

@ai_machinelearning_big_data
👍1
Only a Matter of Style: Age Transformation Using a Style-Based Regression Model

Github
: https://github.com/yuval-alaluf/SAM

Paper: https://arxiv.org/abs/2102.02754v1

@ai_machinelearning_big_data