The following are some of the things I have worked on that I can publicly share:
Trained and open sourced code completion LLMs end-to-end at Replit.
- Hugging Face Links
- Results V1.5, Results V1
- Blog Post on V1.5
Designed the first version of the standalone service for Replit’s AI Chat and its agentic features.
Before that, I interned on the data science team at a PE firm in Toronto and on an ML team at Carfax.
- A Hacker’s Guide to Building with LLMs: Hacking, training, customizing, and building with LLMs without requiring ridiculous resources
- Top voted Tech Talk at Hack the North 2023
- Hotspot and Binding Residue Prediction Using Embeddings
- Did undergrad research work in 2021-2022 on large transformers for protein sequences, focusing on applications to hotspot predictions. Showed results supporting the feasibility of using embeddings from large models (ESM-1b, ProtT5) for hotspot, binding and non-binding residue prediction.
These are some interesting things that I worked on:
Orientalism in the Music of French Opera, A Technical Research Paper at the Intersection of Music and Continental Philosophy
- Wrote my IB Extended Essay (capstone high school paper) on how music depicts social, cultural and philosophical “intangible” ideas with a technical analysis on 19th century French Opera.
- Led the backend team for a web app to search for medicines, ventillators and other supplies for Covid related emergencies for India. 240K+ users used the app.
- Requested by auther to setup basic data modelling code to verify a theory of varying physical constants in the paper: “Cosmology with relativistically varying physical constants” by Rajendra P. Gupta, published in the Monthly Notices of the Royal Astronomical Society, staa2472, https://doi.org/10.1093/mnras/staa2472, 25 August 2020.
- This early work later led to results supporting a theory claiming the universe is twice as old as currently known: https://phys.org/news/2023-08-universe-theory-believed.html.
- Implemented StylePoseGAN paper on top of lucidrains’ stylegan2-pytorch and trained the GAN-based network from scratch. We were trying to build a product that enables users to pay and get new, AI-generated, realistic photos for their social media, Tinder, etc. in 2021 before StableDiffusion etc. we released.
- Built web scrapers to get 800K+ training images from ecommerce sites paired on identity, and built the custom data processing pipeline to assemble curated train and custom eval sets.