Sanjaya’s Blog

Deep learning, machine learning, big data, programming

Senior Data Scientist

Token Embedding Pruning for Sentence Transformers

14 minute read

Can we shrink embedding models by removing redundant token embeddings?

21 minute read

Triplet Loss and Online triplet mining for metric learning

13 minute read

Explore Greedy, Top P and Top K sampling strategies in Generative Language Models

12 minute read

Let’s implement a Transformer Decoder Layer from scratch using Pytorch

10 minute read

Let’s implement a Transformer Encoder Layer from scratch using Pytorch

9 minute read

Understand why masking is needed in Transformer Encoder and Decoder networks and how they are used

30 minute read

Let’s implement Multi-Head Attention from scratch with visual examples

8 minute read

Let’s explore why we need non-linear activation functions in Neural Networks

12 minute read

Learn the algorithm that powers machine learning models such as LLMs and Diffisuion models

8 minute read

Train a NER model with your own data using Huggingface transformers library

8 minute read

Learn how to fine tune a model to compute image similarity using Triplet loss

6 minute read

Learn how to use deep neural networks to implement image search