Blog | Gopikrishna Pavuluri

Blog

System

  • A social Network Portal for Lease Transfer.

    This is the hackthon project we have done at UT Austin.

    Inspiration

    When a national/international student get admit to the university the next things come to mind is space to live? And starts looking for the rooms available near university, to find the rooms one must highly relay on the WhatsApp groups (limited number of users in group and should have an invitation link to join), and the facebook groups (which are out of hand with so many groups available). We want to build a single place community that connects the student who is searching for room with the student who is willing to transfer his lease.

  • A Efficient Portal For Course Registraion System.

    Inspiration

    When a national/international student get admit to the university the next things come to mind is space to live? And starts looking for the rooms available near university, to find the rooms one must highly relay on the WhatsApp groups (limited number of users in group and should have an invitation link to join), and the facebook groups (which are out of hand with so many groups available). We want to build a single place community that connects the student who is searching for room with the student who is willing to transfer his lease.

Deep Learning

LLM From Scratch

  • Part 2:Tokenization - Byte Pair Encoding Training

    In the previous post we talked about subword tokenization and using Byte Pair Encoding (BPE) to train on a large corpus of data. Don’t get confused by the word “training” here — it’s not training a neural network. You’re running an algorithm that produces a vocabulary and a set of merge rules, which a BPE tokenizer then uses to encode and decode text before it ever reaches the transformer.

  • Part 1:Tokenization - The First Step Every LLM Takes

    Before we jump into the key details, here are a few keywords I will be using throughout these articles. It is best to understand them first.