# @dataengineeringtamil on Instagram

- **Type:** Video
- **Original URL:** https://www.instagram.com/p/DNf_oSlIWf1
- **Gondola URL:** https://gondola.cc/posts/63366479-dataengineeringtamil-instagram
- **Thumbnail:** https://img.gondola.cc/tr:w-,h-,fo-auto/postThumbnails/d0e6591bf7.jpg
- **Posted:** 2025-08-18T14:38:14.000+00:00
- **Account Owner:** Data Engineering Tamil (@dataengineeringtamil) — https://gondola.cc/dataengineeringtamil

## Caption

📚 Ever wondered how LLMs like ChatGPT understand text?

In this reel, I break down how vocab.json and merges.txt work behind the scenes using Byte Pair Encoding (BPE)! 🔍
Bonus: I also show you how to train your own vocab.
A must-watch for AI and NLP enthusiasts! 🚀

👨‍💻 Watch now & upgrade your AI game!

Follow me @dataengineeringtamil

Hashtags (all in one line):
#LLM #AI #Tokenizer #vocabjson #mergestxt #BytePairEncoding #ArtificialIntelligence #MachineLearning #DataEngineering #NLP #DeepLearning #AIExplained #GowthamSB #SBGowtham #TheDataTech #aiintamil #genaitamil

## Stats

- **Views:** 4,653
- **Likes:** 432
- **Shares:** 0
- **Comments:** 28

## Tags

bytepairencoding, llm, dataengineering, tokenizer, machinelearning, sbgowtham, nlp, genaitamil, thedatatech, aiexplained, gowthamsb, deeplearning, vocabjson, aiintamil, ai, artificialintelligence, mergestxt

---
Copyright (c) Gondola