# llms.txt for https://adarshdubey.com
# Generated: 2025-02-22
# See https://llmstxt.org/ for specification

## SITE
Name: Adarsh Dubey
Description: Personal portfolio blog of a Full Stack AI Engineer
Author: Adarsh Dubey
URL: https://adarshdubey.com

## CONTENT
Type: Technical blog posts, project documentation, tutorials, and research notes
Topics: Machine learning, deep learning, NLP/LLMs (BPE tokenization, fine-tuning, SLMs),
        web development (Next.js, React, TypeScript, Tailwind CSS), system design,
        tooling and infrastructure, developer productivity, open source contributions
Content style: Practical, hands-on tutorials with code examples; deep dives into ML concepts;
               project post-mortems and build logs; opinion pieces on industry trends
Blog posts: 20+ published articles covering:
    - BPE tokenizer implementations and theory
    - Gemma model fine-tuning and optimization
    - Small language model research
    - Next.js and React best practices
    - NumPy and autograd systems
    - Terminal workflow and developer tools
Projects documented:
    - Facet: Gemma finetuner with efficiency focus
    - Incligrad: Custom autograd engine
    - Inclinet: Scratch-built neural network library
    - Anon: Privacy-first anonymous forum
License: Creative Commons Attribution-NonCommercial-ShareAlike 4.0 (CC BY-NC-SA 4.0)
RSS Feed: https://adarshdubey.com/rss.xml
Sitemap: https://adarshdubey.com/sitemap.xml

## OWNER
Name: Adarsh Dubey
Bio: Full Stack AI Engineer and Machine Learning Engineer with a passion for building
     in public and exploring the frontiers of LLMs. Currently contributing to Google DeepMind
     as a GSoC '25 contributor and serving as a core team member at WeMakeDevs community.

     Expertise spans machine learning, natural language processing, and modern web development.
     Actively researching and experimenting with small language models, fine-tuning techniques,
     and efficient inference methods. In web development, specializes in Next.js, React, TypeScript,
     and building performant, accessible user interfaces.

     Notable open source projects:
     - Facet: A Gemma finetuning tool for efficient model adaptation
     - Anon: An anonymous discussion platform built for privacy-focused communities
     - Inclinet: A custom neural network library from scratch
     - Incligrad: An automatic differentiation engine for gradient computation

     Philosophy: Strong advocate for open source, developer education, and sharing knowledge
     through technical blog posts and community contributions. Believes in the power of
     transparent, reproducible research and development.

Contact:
  - GitHub: https://github.com/inclinedadarsh
  - LinkedIn: https://linkedin.com/in/dubeyadarsh/
  - Twitter: https://x.com/inclinedadarsh
  - Website: https://adarshdubey.com
  - Cal.com: https://cal.com/adarshdubey

## AI USAGE POLICY
Allowed: Yes, with attribution
Conditions:
  - Attribution to Adarsh Dubey and https://adarshdubey.com
  - Non-commercial use only
  - Share-alike for derivative works
Not Allowed: Commercial use without explicit permission
Contact for permissions: DM on Twitter/X (@inclinedadarsh) or GitHub

## TECHNICAL
Stack: Next.js 16, React 19, TypeScript, Tailwind CSS v4
CMS: Markdown files (MDX) stored in repository
Update frequency: Regular (blog posts ~monthly, commits frequent)