Skip to content
View ffenix7's full-sized avatar
17 followers · 30 following

Achievements

Achievement: Pull Shark

Achievements

Achievement: Pull Shark

Highlights

  • Pro

Block or report ffenix7

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
ffenix7/README.md

👋 Hi, I'm Filip Gębala

I'm a student and enthusiast of AI, living in Kraków, Poland. Currently, I am working on preparing for "Olimpiada o Diamentowy Indeks AGH" in maths.

🎯 Current Goals & Projects

🔬 Current Research

  • Fine-tuning models for specialized tasks using Parameter-Efficient techniques (PEFT).

Current Projects

  • AI assistant for planning running workouts

💡 Featured Projects

  • HypeLoRA: A Parameter-Efficient technique for Encoder Transformer calibration. Accepted into PP-RAI conference.
  • ByteTorch: A lightweight deep learning framework inspired by PyTorch, featuring a minimal autograd engine.

🧠 AI Focus Areas

  • Automatic Speech Recognition
  • Natural Language Processing
  • Model optimization and error analysis
  • Computer Vision (segmentation, object detection)

🎓 Study groups

  • AI Olympiad Club at Jagiellonian University - projects and research with top polish scientists
  • MIKO (community of top AI Olympiad laureates)

🏆 Awards & Achievements

  • Motorola Science Cup 2025 - 2nd place (programming stage)
  • HackArena 3.0 - 8th place / 33 teams (5th place in the Grand Finale)
  • Ensemble Hackathon 2025 - 8th place / 40 teams
  • Ensemble Hackathon 2026 - 11th place / 50 teams

🎓 Education

  • Technical School of Communications in Cracow - the best technical school in Poland

📬 Contact

⭐️ "Per aspera ad astra"

Pinned Loading

  1. btrojan-official/HypeLoRA btrojan-official/HypeLoRA Public

    HypeLoRA: Hypernetwork-Generated LoRA Adapters for Calibrated Language Model Fine-Tuning

    Python 15

  2. ByteTorch ByteTorch Public

    ByteTorch is a lightweight deep learning framework inspired by PyTorch, featuring a minimal autograd engine

    Jupyter Notebook

  3. Kminek2/HotdogsRun Kminek2/HotdogsRun Public

    Wonderfull 3D racing game. Made in own game engine using Vulkan and C++.

    C++ 4

  4. HackArena3 HackArena3 Public

    Python 1