haoxing-du

ay250-homework

Homework for the Spring 2022 iteration of Astro 250 (Python Seminar for Data Science) at Berkeley https://github.com/profjsb/python-seminar

compulsive-lm

Playing with RL fine-tuning of large language models. What if I fine tune the model to always output a certain word?

facts-in-llms

Investigate how facts are represented in GPT-2 small. MLAB Week 4 project.

gpt2-web-app

A web tool for looking for behaviors of GPT-2 small. Available at https://modelbehavior.ngrok.io/

haoxing-du.github.io

My personal website. Check it out at haoxingdu.com

pg-tools

I'm another paragliding pilot who codes

ray-tracer

Python ray tracer following the Ray Tracer in One Weekend tutorial: https://raytracing.github.io/books/RayTracingInOneWeekend.html

toy-flow

Using normalizing flows to unify simulation and inference at the LHC.

toy-flow-demo

Final project for AY250

ToyFlow

haoxing-du/haoxing-du.github.io

My personal website. Check it out at haoxingdu.com

haoxing-du/ay250-homework

Homework for the Spring 2022 iteration of Astro 250 (Python Seminar for Data Science) at Berkeley https://github.com/profjsb/python-seminar

haoxing-du/compulsive-lm

Playing with RL fine-tuning of large language models. What if I fine tune the model to always output a certain word?

haoxing-du/facts-in-llms

Investigate how facts are represented in GPT-2 small. MLAB Week 4 project.

haoxing-du/gpt2-web-app

A web tool for looking for behaviors of GPT-2 small. Available at https://modelbehavior.ngrok.io/

haoxing-du/pg-tools

I'm another paragliding pilot who codes

haoxing-du/ray-tracer

Python ray tracer following the Ray Tracer in One Weekend tutorial: https://raytracing.github.io/books/RayTracingInOneWeekend.html

haoxing-du/toy-flow

Using normalizing flows to unify simulation and inference at the LHC.

haoxing-du/toy-flow-demo

Final project for AY250

haoxing-du/ToyFlow

haoxing-du/weak-to-strong