Ajeesh Garg

@ajeesh

All cardsCollections

GitHub - FareedKhan-dev/all-rag-techniques: Implementation of all RAG techniques in a simpler way

FareedKhan-dev github.com

Langchain and RAGs

All RAGs

Implementing Self-Attention from Scratch in PyTorch

Medium mohdfaraaz.medium.com

Vision Transformers and

Implementing Self-Attention from Scratch in PyTorch

Another medium article: The Easiest Way to Understand Self-Attention with Code.

google.com

Attention and

SAM model

How to Use the Segment Anything Model (SAM)

Piotr Skalski blog.roboflow.com

Vision Transformers and

Transformers from Scratch

Attention and Transformers

links:

1. Training Transformers from Scratch: A Deep Dive Guide | by Devang Vashistha | in Data Science Collective - Freedium

2. https://differ.blog/p/here-s-how-you-can-build-and-train-gpt-2-from-scratch-using-pytorch-ace4ba

MAE is less sensitive to outliers but I am still trying to mae as my loss function? Why do you think someone might choose MAE as the loss but still monitor MSE as a metric? What behavior during training might that help catch?

My data distribution is really sparse so as my data distribution is more sparse i choose mae over mse. Basically, it will app

Loss and Loss function

Loss Function notes - mae

arxiv.org

Transformers and

Vision TransFormers original paper

Just a moment...

Mriganka Nath mrinath.medium.com

Vision Transformers and

Patchifying Images for Computer Vision

Transformers Explained Visually (Part 1): Overview of Functionality | Towards Data Science

towardsdatascience.com

Attention and

Transformers Explained Visually I