Skip to content
View Jac-Zac's full-sized avatar
🎯
Focusing
🎯
Focusing
19 followers · 24 following

Achievements

Achievement: Pair ExtraordinaireAchievement: StarstruckAchievement: Pull Sharkx2Achievement: Arctic Code Vault Contributor

Achievements

Achievement: Pair ExtraordinaireAchievement: StarstruckAchievement: Pull Sharkx2Achievement: Arctic Code Vault Contributor

Highlights

  • Pro

Block or report Jac-Zac

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Jac-Zac/README.md

Jac-Zac ⌘

I'm a Master's student in Data Science & AI with a focus on deep learning and mechanistic interpretability. I have several repos covering different projects for both personal interest and research.

More Information About Me 🔎 

 id && whoami && uname -a
Learn More About Me 🧐 > I try to keep up-to-date with major ML and DL papers while learning more every day.
  • 🤖 I'm currently doing a master's in Data Science & AI at the University of Trieste.
  • 🔭 I spend most of my time studying and learning new things (currently focused on mech-interp).
  • 🌱 I have recently worked with CUDA on self-attention (building it toward a FlashAttention-style implementation).
  • 💬 Ask me about anything tech-related / ML / DL (if you ask me something I can't answer, that's great — it means I'll learn 📚).

I try to always keep myself busy with something. I guess this kind of shows it...

Jac-Zac's activity graph

🪴 Things I like, such as editors and languages:

Skills: Neovim, PyTorch, Python, Bash, C

Pinned Loading

  1. implicit-personalization/persona-vectors implicit-personalization/persona-vectors Public

    Building pipeline for extracting steering vectors.

    Python

  2. BayesianFlow BayesianFlow Public

    This is the final project for the Probabilistic Machine Learning and Deep Learning course. In this project, we explore, analyze, and re-implement the methodology presented in the paper:

    Jupyter Notebook

  3. Self_Attention_Kernels Self_Attention_Kernels Public

    This project implements Causal Multi-Head Self-Attention (CMHSA) with three backends: a single-threaded CPU version, a multi-threaded CPU version, and a GPU-accelerated version.

    Cuda 2

  4. Stat_Missing_Data_Project Stat_Missing_Data_Project Public archive

    This project focuses on analyzing Missing data patterns using simulated datasets. And then extending the research to a real dataset

    HTML 1

  5. ML_Project_LoRA ML_Project_LoRA Public archive

    LoRA implementation in Tinygrad

    Python 2

  6. micrograd_cpp micrograd_cpp Public archive

    An implementation of https://github.com/karpathy/micrograd in c++

    C++ 1