Harsimar Singh·Oct 28Part 3: Tokenization is important in LLMTokenization: Why Your LLM Has Never Read a Single LetterA response icon1A response icon1
Harsimar Singh·Oct 27Part 2 : The big picture of LLMInside the LLM · Part 2 of 30. One sentence’s journey through a language model, one small idea at a time.
Harsimar Singh·Oct 26Part 1 : A brief history of LLMPart 1/30: Every AI chatbot you’ve used is playing a 75-year-old guessing game.A response icon1A response icon1
Harsimar Singh·Jul 7AI in PanjabiI am putting up little effort in establishing a course of AI in panjabi on github.
Harsimar Singh·Sep 9, 2025Top Leetcode questions for your dream companyHere are the top questions on leetcode that you can practice to crack DSA round of interviews. These are divided into the categories as…
Harsimar Singh·Aug 25, 2025How I made deepseek V3.1 explore infinity tokens in genera?Some models are still naive at making the interpretation of input images like Deepseek V3.1 . The output is given out to be a base64…
Harsimar Singh·Sep 12, 2024How HuggingFace tokenizer gets executed through maze of code?I was very much intrigued about hugging face’s core concept of loading models and running it. It does everything under the hood and you…
Harsimar Singh·Aug 29, 2024Information Retrieval : Chapter 2In this we will talk about vocabulary and postings list. In previous post of chapter 1, I wrote notes about very fundamental process of…
Harsimar Singh·Aug 26, 2024Information Retrieval : Chapter 1I didn’t think of this, but this started as a series of short notes on information retrieval by Prof. Christopher D. Manning, Prabhakar…
Harsimar Singh·Aug 20, 2024Mixture of Models vs Dense Transformers?Recently meta has released their “Herd of LLama Models” and highlight of which is 405B parameter model contributing significantly to the…
