CerebriumTrain models like Stable Diffusion and Bloom (175B) using your own computerOver our last few posts we have been mentioning the hype around Large Language and Generative AI models and how you can decrease both…Feb 20, 2023Feb 20, 2023
InPyTorch Lightning Developer BlogbySean NarenthiranLightning Transformers 0.2 — New 🤗Tasks, Community Features and Big Model Training & InferencePairing 🤗 Transformers and Lightning has become increasingly popular, leveraging Lightning to hide away the boilerplate of your training…Nov 29, 2022Nov 29, 2022
InGeek CulturebyNick SaraevAI killed the piano starPlus: how to beat GPT-3 performance at 1% of the cost.Nov 10, 20223Nov 10, 20223
Sik-Ho TsangBrief Review — Longformer: The Long-Document TransformerLongformer, Global Attention and Attention Within Sliding WindowOct 29, 20221Oct 29, 20221
Sik-Ho TsangBrief Review — PPBERT: A Robustly Optimized BERT Pre-training Approach with Post-trainingPPBERT: Pretraining+Post-Training+Fine-Tuning for BERTJan 14, 2023Jan 14, 2023
InGeek CulturebyThe PyCoachI Spent 14 Days Testing ChatGPT. Here Are 3 Ways It Can Improve Your Everyday LifeAfter exploring all the things you can do with this AI-Powered chatbot, I found these to be the most useful.Dec 15, 202234Dec 15, 202234
InTDS ArchivebyMario LarcherPaper Explained — Instant Neural Graphics Primitives with a Multiresolution Hash EncodingThe seminal NeRF paper has taken the computer vision community by storm, but the proposed approach requires hours of training for every…Jul 20, 2022Jul 20, 2022
InTDS ArchivebyJames BriggsQuick-fire Guide to Multi-Modal ML With OpenAI’s CLIPLearn how to translate between text to image and back again with CLIP and vector embeddingsAug 11, 20221Aug 11, 20221
InTDS ArchivebyFrancesco ZuppichiniImplementing RepVGG in PyTorchMake your CNN >100x fasterJul 26, 2022Jul 26, 2022
InTDS ArchivebyJames LoyA Comprehensive Guide to Microsoft’s Swin TransformerIn-depth Explanation and AnimationsMay 20, 20228May 20, 20228
InTDS ArchivebySamuele MazzantiYour Dataset Is Imbalanced? Do Nothing!Class imbalance is not a problem. Debunking one of the most widespread misconceptions in the ML community.Aug 24, 202229Aug 24, 202229
InTDS ArchivebyFrancesco ZuppichiniImplementing SegFormer in PyTorchA fast, efficient, and lightweight model for image segmentationMay 3, 20224May 3, 20224
Sik-Ho TsangReview — ResT: An Efficient Transformer for Visual RecognitionResT / ResTv1, Design Efficient Multi-Head Self-Attention (EMSA) Using Depth-Wise ConvolutionOct 27, 2022Oct 27, 2022
Jim Clyde MongeUse This FREE AI Tool To Upscale Your AI-Generated ImagesHere’s a free Latent-Diffusion AI tool that can increase the size of your image by a factor of up to four.Aug 29, 202215Aug 29, 202215
InTDS ArchivebyAndrew BlanceUsing AI to Generate 3D Models, Fast!How to use NVIDIA’s NeRF code to create 3D modelsJul 27, 20226Jul 27, 20226
HPC-AI TechTrain 18-billion-parameter GPT models with a single GPU on your personal computer!When it comes to training large AI models, people will think about using thousands of GPUs, expensive training costs, and only a few tech…May 16, 20221May 16, 20221
InTowards AIbySergi Castella i SapéTrends in AI — August 20223% of Google’s new code is written by a Language Model, DeepSpeed for doing inference with Trillion-scale Mixture of Experts, Beating…Aug 5, 20221Aug 5, 20221
