https://github.com/muhtasham/muhtasham
https://github.com/muhtasham/muhtasham
Last synced: 5 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/muhtasham/muhtasham
- Owner: Muhtasham
- Created: 2022-02-24T23:24:42.000Z (over 4 years ago)
- Default Branch: main
- Last Pushed: 2024-05-29T12:01:56.000Z (about 2 years ago)
- Last Synced: 2025-03-20T16:19:36.199Z (about 1 year ago)
- Size: 66.4 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
### Hello world!
Blog: https://muhtasham.github.io/blog/
🔗 More about work experience in my [LinkedIn](https://www.linkedin.com/in/muhtasham/)
### Education 🎓
- **Master’s degree** at Technical University of Munich
- Sequential Multi-task Learning in NLP with Focus on RegTech Domain
- **Bachelor's degree** at Sabanci University
- [Diploma thesis](https://github.com/osmanberke/Deep-SSVEP-BCI): "A Deep Neural Network for SSVEP-based 🧠 Computer Interfaces"
- [Featured in ML Monthly YouTube Show](https://youtu.be/cNDA60YLVdQ?t=251)
### Projects 🚀
- 📑 [StarCoder- May the Source be with you](https://drive.google.com/file/d/1cN-b9GnWtHzQRoE7M7gAEyivY0kl4BYs/view) - The StarCoder models are 15.5B parameter models trained on 80+ programming languages from The Stack (v1.2), with opt-out requests excluded. The model uses Multi Query Attention, a context window of 8192 tokens, and was trained using the Fill-in-the-Middle objective on 1 trillion tokens.
- 📑 [ECOC based Multi-Class Classification for BCI](https://ieeexplore.ieee.org/abstract/document/9531496) - Developed DNN, under ECOC framework to detect the character out of 40 possibilities that the (disabled) subject wants to communicate via Brain Computer Interface (BCI).
- 📑 [Fault-Tolerant Strassen-Like Matrix Multiplication](https://ieeexplore.ieee.org/document/9302383) - Designed parity calculations to make matrix multiplication calculations, using Strassen-Like algorithms on cloud computing environment (with parallel setting) fault-tolerant.
- 📑 [TajGPT and TajBERTo](https://wandb.ai/muhtasham/tajberto/reports/My-learnings-from-training-TajBERTo--VmlldzoyMTEyNDQx) - Developed first ever RoBERTa-like language model based on Tajik language after extensive filtering of the dataset. The model can be used for masked text generation or fine-tune it to a downstream task.