Skip to content
View NinoRisteski's full-sized avatar
🎯
🎯
45 followers · 48 following

Achievements

Achievement: StarstruckAchievement: Pair Extraordinairex3Achievement: YOLOAchievement: Pull Sharkx2Achievement: Quickdraw

Achievements

Achievement: StarstruckAchievement: Pair Extraordinairex3Achievement: YOLOAchievement: Pull Sharkx2Achievement: Quickdraw

Block or report NinoRisteski

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.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

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

Report abuse
ninoristeski/README.md

Hi there 👋

Personal blog.📓

Seeking an ML Engineer Role — Contact me at [email protected]!

Latest Projects

  • 👨‍🚀tinypilot: AI agent that helps you learn the tinygrad codebase and updates you on the latest bounties.

  • 👨‍🔬HubermanAnswers: Ask questions, get answers straight from Dr. Andrew Huberman’s podcasts - an AI agent that uses NLP to deliver context-aware responses from podcast transcripts.

  • 👨‍💻ShallowFlow: Lightweight LLM training framework focused on cost-effective training on local GPU and AWS.(In progress)

  • 🤖transformer-from-scratch: From-scratch implementation of the Transformer architecture from the "Attention is All You Need" paper, built with PyTorch.

  • 🦾GPTmashina: GPT2 built from scratch for learning purposes. Optimized with training speedups: Flash Attention, mixed precision (bfloat16), model compilation with torch.compile, and cloud GPU deployment on V100.

Currently:

  • Learning the nuts and bolts (GPU/Compiler part) of tinygrad.
  • Building end-to-end ML projects that solve personal and practical challenges.
  • Contributing to open-source (Unsloth, Browser-Use...).

Pinned Loading

  1. tinypilot tinypilot Public

    AI agent that helps you learn Tinygrad and updates you on the bounties

    Python 1

  2. HubermanAnswers HubermanAnswers Public

    Ask Dr. Andrew Huberman questions and receive answers directly from his podcast episodes.

    Python 16 1

  3. ShallowFlow ShallowFlow Public

    Simple distributed LLM training framework optimized for cost-effective training on local GPU and AWS T4

    Python

  4. transformer-from-scratch transformer-from-scratch Public

    PyTorch implementation of the transformer architecture from the paper 'attention is all you need'

    Python