Uygar Kurt

3.86K subscribers

32 videos

AI researcher and engineer. I created this channel to share my technical knowledge and share some projects I do. It's still very new and small channel. Singl...

Latest Videos

mHC Explained Stable Hyper-Connections for Large Language Models

GLM-4.5 Deep Dive - The Bag of Tricks Behind the Model (Paper Explained)

ReLU Activation in CUDA - Tensara Solutions (GPU Programming)

Hinge Loss in CUDA - Tensara Solutions (GPU Programming)

Vector Addition in CUDA - Tensara Solutions (GPU Programming)

Implement and Train VLMs (Vision Language Models) From Scratch - PyTorch

How to Benchmark LLMs Using LM Evaluation Harness - Multi-GPU, Apple MPS Support

PyTorch Dimensions Explained – The Only Guide You Need!

Estimate Carbon Footprint and Energy Consumption of ML Models and LLMs - HuggingFace, CodeCarbon

Fine-Tune Visual Language Models (VLMs) - HuggingFace, PyTorch, LoRA, Quantization, TRL

Implement Llama 3 From Scratch - PyTorch

Model Merging Merge LLMs to Create Frankestein Models - Python, HuggingFace, Mergekit

Conversational Memory for LLMs Using LangChain and Huggingface - Python

Instruct-Tune Llama to Create ChatGPT Like Chatbots Custom Dataset, Huggingface, SFT

Train Diffusion Model For Image Generation PyTorch, Diffusers, Custom Dataset

Implement and Train DCGAN From Scratch for Image Generation - PyTorch

Lip-Sync With AI Video-Retalking

Transformer Based Punctuation Restoration for Turkish - Paper Presentation

Atatürk'ün Yapay Zeka Tarafından Üretilen Sesiyle Gençliğe Hitabe - Cumhuriyetin 100. Yılı Projesi

A Modern Turkish Poet Fine-Tuned GPT-2 - Paper Presentation

ViT (Vision Transformer) - An Image Is Worth 16x16 Words (Paper Explained)

100 Subscribers Special. Thank You!

Implement and Train ViT From Scratch for Image Recognition - PyTorch

Kaggle Competition Walkthrough [NLP] - CommonLit Evaluate Student Summaries

Kaggle Competition Walkthrough [NLP] - U.S. Patent Phrase to Phrase Matching

Kaggle Competition Walkthrough [NLP] - CommonLit Readability Prize

LoRA BERT vs Non-LoRA BERT Comparison and Implementation

Fine-Tune BERT For Question-Answering(Q&A) - PyTorch & HuggingFace

Implement and Train U-NET From Scratch for Image Segmentation - PyTorch

Scaled Dot Product Attention Explained + Implemented