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
Microsoft's ProphetNet-X: Large-Scale Pre-training Models for English, Multi-lingual, Dialog, and Code Generation

Code: https://github.com/microsoft/ProphetNet

Paper: https://arxiv.org/pdf/2001.04063.pdf

@ai_machinelearning_big_data
TediGAN: Text-Guided Diverse Face Image Generation and Manipulation in PyTorch.

Github: https://github.com/IIGROUP/TediGAN

Dataset: https://github.com/IIGROUP/Multi-Modal-CelebA-HQ-Dataset

Paper: https://arxiv.org/abs/2104.08910v1

@ai_machinelearning_big_data
This media is not supported in your browser
VIEW IN TELEGRAM
🌐 MMDetection3D is an open source object detection toolbox based on PyTorch, towards the next-generation platform for general 3D detection

Github: https://github.com/open-mmlab/mmdetection3d

Paper: https://arxiv.org/abs/2104.10956v1

@ai_machinelearning_big_data
Token Labeling: Training a 85.4% Top-1 Accuracy Vision Transformer with 56M Parameters on ImageNet

Github: https://github.com/zihangJiang/TokenLabeling

Paper: https://arxiv.org/abs/2104.10858v2

@ai_machinelearning_big_data
🚀 This is an open source toolkit called s3prl, which stands for Self-Supervised Speech Pre-training and Representation Learning

Github: https://github.com/s3prl/s3prl

Paper: https://arxiv.org/abs/2105.01051v1

@ai_machinelearning_big_data