/ab-hee-shake/
Hardware based Machine Learning | Reinforcement Learning | LLM
I am deeply interested in LLMs and the math behind how they work. My ongoing research involves fine-tuning LLM for Verilog RTL, and I actively contribute to Apple’s CoreML tools. During my free time, I write blogs on what I find interesting — more of LLMs, Reinforcement Learning Fine Tuning, and State-of-the-art work in the field of machine learning.