Finding the signal in the noise.

Data science major, engineer by habit. I build apps and systems to make life easier for people like me — and work with ML systems. All in service of designing and building meaningful software.

LEARNING_CURVE.PNG · TRENDING UP

Read my case study → More about me

Currently

Training Pretraining RQwen3 on UNC’s Longleaf L40S partition.
Writing Drafting the architecture deep-dive (Act 2 of the RQwen3 case study).
Reading Recent pretraining methodology and small-model behavior papers.

01

Featured work

Case study · ML Infrastructure

I Rebuilt Qwen3 From Scratch and Pretrained It on a University Supercomputer

Reconstructed Qwen3-0.6B's architecture component-by-component (751M params), built a 13B-token curated data pipeline, and pretrained it on UNC's Longleaf L40S partition.

Read the case study →