Yeraly Gainulla 
Aspiring AI engineerSchool student at Aqbobek Lyceum
Aktobe, Kazakhstan
Email: eralygainulla [at] gmail [dot] com
|
|
Yeraly Gainulla
Aspiring AI engineer |
I am a high school student at Aqbobek Lyceum in Aktobe, Kazakhstan. My research interests primarily in machine learning, with a focus on natural language processing (NLP). I am passionate about exploring how AI models can be optimized and trained.
Currently, I am working on several independent projects, including KazBERT and AI code detection. I am also preparing for international AI olympiads to strengthen my theoretical foundations and problem-solving skills. My long-term goal is to contribute to research in machine learning and pursue an academic path in AI.
Against Toxic Telegram – Against Toxic Telegram Bot is a Telegram bot designed to automatically analyze and delete toxic messages in groups and channels. [repo]
E-sense.cv – A computer vision startup, app and a Telegram bot designed to help parents monitor their children's emotional state. [repo]
KazBERT – BERT-based model fine-tuned for Kazakh language tasks. The model is trained using Masked Language Modeling (MLM) on a Kazakh, Russian, English text corpus. [repo]
Skin-AI – Skin-AI is a deep learning model based on ConvNeXt, optimized for skin disease classification using PyTorch Lightning. [repo]