# @awomanindatascience on Instagram

- **Type:** Video
- **Original URL:** https://www.instagram.com/p/DIDDTD9JOOd
- **Gondola URL:** https://gondola.cc/posts/61230123-awomanindatascience-instagram
- **Thumbnail:** https://img.gondola.cc/tr:w-,h-,fo-auto/postThumbnails/d8df3511b8.jpg
- **Posted:** 2025-04-05T02:12:47.000+00:00
- **Account Owner:** Chinar Arora (@awomanindatascience) — https://gondola.cc/awomanindatascience

## Caption

🌴Today’s day 3/30 days of Building a Large Language Model from Scratch.
I focused on preparing the training dataset today. 
This involves splitting text into individual word and sub word tokens which can then be encoded into vector representations for the LLM.
🌴Deep neural network models can’t process raw text directly. Therefore we need a way to represent words as continuous values vectors. The concept of converting data into a vector format is often referred to as embedding. 
🌴The steps require for preparing the embedding include splitting text into words, converting words into tokens and turning tokens into embedding vectors.
🌴The text I tokenize for this LLM training is “The Verdict”, a short story by Edith Wharton which has been released into the public domain.
Tomorrow I’ll convert them into embedding. 

#deeplearning #generativeai #30dayschallenge #womenwhocode  #datascience #womenintech

## Stats

- **Views:** 0
- **Likes:** 50
- **Shares:** 0
- **Comments:** 1

## Tags

womenwhocode, generativeai, datascience, womenintech, deeplearning, 30dayschallenge

---
Copyright (c) Gondola