---
title: "Shreshtha Modi (@shreshtha) | Hashnode"
description: "Engineer, Developer. Read the latest articles by Shreshtha Modi on Hashnode."
url: "https://hashnode.com/@shreshtha"
---

@shreshtha

# Shreshtha Modi

@shreshtha · Gujarat, India · Joined September 2021

Engineer, Developer

### [Stop Interrupting "Matlab...": Building a Turn Detector for Hinglish Voice AI](https://shreshtha.hashnode.dev/stop-interrupting-matlab-building-a-turn-detector-for-hinglish-voice-ai?utm_source=hashnode&utm_medium=feed)

Turn detectors are basically voice models which tell you when the user is done speaking. Traditional turn detectors have been trained on english data and have poor capability to distinguish between wh

7 min read · [shreshtha.hashnode.dev](https://shreshtha.hashnode.dev/stop-interrupting-matlab-building-a-turn-detector-for-hinglish-voice-ai?utm_source=hashnode&utm_medium=feed)

[Aug 22](https://hashnode.com/posts/stop-interrupting-matlab-building-a-turn-detector-for-hinglish-voice-ai/6a8a0349b0a0ef70a7f3ddd7)

### [Does optimizing context actually make a reasoning model think less?](https://shreshtha.hashnode.dev/does-optimizing-context-actually-make-a-reasoning-model-think-less?utm_source=hashnode&utm_medium=feed)

Introduction LLMs have become very popular, with one big use case being people asking questions by just providing the context along with them. In this article, we analyze how Gemini's frontier reasoni

8 min read · [shreshtha.hashnode.dev](https://shreshtha.hashnode.dev/does-optimizing-context-actually-make-a-reasoning-model-think-less?utm_source=hashnode&utm_medium=feed)

[Aug 15](https://hashnode.com/posts/does-optimizing-context-actually-make-a-reasoning-model-think-less/6a80ae4be0ea0c989db4047e)

### [Approximating Faster Transformers](https://shreshtha.hashnode.dev/approximating-faster-transformers?utm_source=hashnode&utm_medium=feed)

A comprehensive overview of sketching and sampling algorithms for DistilBERT.

27 min read · [shreshtha.hashnode.dev](https://shreshtha.hashnode.dev/approximating-faster-transformers?utm_source=hashnode&utm_medium=feed)

[Jun 6](https://hashnode.com/posts/approximating-faster-transformers/6a24449ee4962c42457221e0)

### [A beginner's guide to fine tuning language models without a GPU](https://shreshtha.hashnode.dev/a-beginners-guide-to-fine-tuning-language-models-without-a-gpu?utm_source=hashnode&utm_medium=feed)

Learn how to fine-tune language models without a GPU using a beginner's guide. Explore techniques and tools for efficient tuning

11 min read · [shreshtha.hashnode.dev](https://shreshtha.hashnode.dev/a-beginners-guide-to-fine-tuning-language-models-without-a-gpu?utm_source=hashnode&utm_medium=feed)

[Mar 31, 2024](https://hashnode.com/posts/a-beginners-guide-to-fine-tuning-language-models-without-a-gpu/662cd18b64880ee52212e691)

### [A layman's guide to Large Language Models](https://shreshtha.hashnode.dev/a-laymans-guide-to-large-language-models?utm_source=hashnode&utm_medium=feed)

If you've been anywhere on the internet lately, chances are you've been swept up in the whirlwind of OpenAI, particularly its brainchild, ChatGPT. But what exactly is ChatGPT, or any large language model for that matter? In this article, I attempt to...

10 min read · [shreshtha.hashnode.dev](https://shreshtha.hashnode.dev/a-laymans-guide-to-large-language-models?utm_source=hashnode&utm_medium=feed)

[Mar 25, 2024](https://hashnode.com/posts/a-laymans-guide-to-large-language-models/6601a85e4d2bad105d294efe)
