Understanding Positional Information in Modern Neural NetworksWe learnt about Transformer models in more details here. Transformer model don’t use recurrence and takes all the inputs all at once, there…4d ago4d ago
Introduction to Agents in LLMsAgents are becoming very popular in today’s world. I wanted to write a simple enough introduction to agents.Jul 22, 2024Jul 22, 2024
Ensembles of Decision TreesEnsembles are a type of machine learning technique that combines multiple models to create a more powerful, accurate, and robust model. Two…Jul 20, 2024Jul 20, 2024
Tokenization in LLMsWhen people start learning about LLMs, this seem to be the most underestimated part. Hence, I thought of this topic for this blog. This is…Jul 4, 2024Jul 4, 2024
Approximate Nearest NeighboursFinding the nearest neighbours is a widespread problem is today’s world. The usecases are Visual Search, recommendations, finding similar…Mar 29, 2024Mar 29, 2024
ML Systems — Recommendations1. Scaling the Instagram Explore recommendations systemDec 11, 20231Dec 11, 20231
Keras (The high-level API for TensorFlow) Cheatsheet — The one stop shopKeras is usually the first framework one learns while starting to get into Deep Learning. It was mine too. But I tend to forget the…Dec 1, 2023Dec 1, 2023
Finetuning LLMs using LoRABefore getting to the meat of the blog i.e. Finetuning an LLM, it will be good to have a brief summary of Why do we even need it ?Sep 29, 20235Sep 29, 20235
LangChain: The Future of LLM-powered Applications — Part 2(Application)In the previous blog, we learnt about the background/basics of Langchain, In this one we will see some use-cases and know about how to…Sep 16, 2023Sep 16, 2023