Latest Blogs

 

Positional Embeddings Implementation

I’d be happy to continue with the Mini-GPT training code. Let’s finish the implementation:

Learning Basics of Tensors

Pytorch
Deep Learning
Linear Algebra
GPU Programming
Change dimension order and inspect stride layout.
Jul 27, 2025
Ismail TG

Manim Project Part 1: Prepare The Dataset

LLM
Instruction Tuning
ManimCE
As part of my exploration into building a prototype that generates Manim animations from natural language descriptions, I came across the bespoke-manim dataset on Hugging Face…
Apr 10, 2025
Ismail TG

Deep Dive into PyTorch Internals: Autograd and torch.fx

Pytorch
Deep Learning
As I continue to deepen my understanding of machine learning systems, I’ve realized that knowing how models run is just as important as knowing how to build them. This post…
Apr 5, 2025
Ismail TG

Chapter 3: Build a Large Language Model

LLM
Deep Learning
An encoder-decoder Recurrent Neural Network (RNN) is a sequence-to-sequence model often used in tasks like machine translation. how it works?: * Encoder: Processes the input…
Dec 5, 2024
Ismail TG

Chapter 2: Build a Large Language Model

LLM
Deep Learning
Breaking Text into Units: Tokenization splits text into smaller pieces called tokens (words, subwords, or characters), which are the building blocks the model uses to…
Nov 16, 2024
Ismail TG

Chapter 1: Build a Large Language Model

LLM
Deep Learning
In this series on notebooks I will share my learning/note-taking of the book Build a Large Lunguage Model(From Scratch) by the Author Sebastian Raschka.
Nov 14, 2024
Ismail TG

Hugging Face Course Notes: Chapter5

Hugging Face
Pytorch
Deep Learning
NLP
LLM
HuggingFaceHub
:::
Feb 27, 2024
Ismail TG

Hugging Face Course Notes: Chapter4

Hugging Face
Pytorch
Deep Learning
NLP
LLM
HuggingFaceHub
In general there’s 3 ways to create a new model reposetories:
Feb 26, 2024
Ismail TG

Multi Choice with Swag Dataset

HuggingFace
Pytorch
NLP
Datasets
To understand each operation of that function we will do it step-by-step:
Nov 28, 2023
Ismail TG

Hugging Face Course Notes: Chapter2

Hugging-Face
NLP
LLMs
Pytorch
we even could use AutoModel instead of BertModel since it will produce agnostic code that fits all situations
Oct 19, 2023
Ismail TG

Hugging Face Course Notes: Chapter3

Hugging-Face
NLP
LLMs
Pytorch
Datasets
Swag
Let’s take a look on pair exmaple from the training dataset:
Oct 19, 2023
Ismail TG

Hugging Face Course Notes: Chapter1

Hugging-Face
NLP
LLMs
In this series I wiil cover notes I took from the Hugging Face NLP course with code snippets and examples.
Oct 18, 2023
Ismail TG

Kaggling Tutorial #0: Download A Dataset from Kaggle Using API-Key

Kaggle
Colab
  • In this mini tutorial we will create a colab notebook and download a Kaggle dataset using Kaggle API-key.
  • Having the possibility to work on different Free computing…
Oct 18, 2023
Ismail TG

Building QAs System Using Haystack

Haystack
LLMs
QAs
NLP
In this tutorial we will try to build a simple Q/A system that can answer questions about specific topic using the **HayStack** library.
Oct 17, 2023
Ismail TG

Utilizing Existing FAQs for Question Answering

Haystack
LLMs
QAs
NLP
Pandas
  • Usually the Extractive Question Answering systems uses pure data-texts to generate answers, but in some cases it we could useful to use them on previous FAQs as dataset
  • Th…
Oct 17, 2023
Ismail TG

Chapter 7: Questionnaire

Fastai
Pytorch
Deep Learning
Q1:
What is the difference between ImageNet and Imagenette? When is it better to experiment on one versus the other?
* ImageNet is dataset with 1.3 million images and 1000…
Oct 31, 2022
Ismail TG

Chapter 7: Deep learning for coders with fastai and pytorch

Fastai
Pytorch
Deep Learning
The idea behind Progressive Resizing is to start training the model with small images, and end the training fase with large images.
Oct 30, 2022
Ismail TG

Chapter 6: Questionnaire

Fastai
Pytorch
Pandas
Deep Learning
Q1:
How could multi-label classification improve the usability of the bear classifier?
Oct 29, 2022
Ismail TG

Chapter 6: Deep learning for coders with fastai and pytorch

Fastai
Pytorch
Numpy
Deep Learning
5011 rows × 3 columns
Oct 29, 2022
Ismail TG

Chapter 5: Questionnaire

Fastai
Pytorch
Deep Learning
Q1:
Why do we first resize to a large size on the CPU, and then to a smaller size on the GPU?
____
* Reisizing images is done image per image on cpu, while transformation is…
Oct 29, 2022
Ismail TG

Chapter 4: Questionnaire

Fastai
Pytorch
Deep Learning
Q1:
How is a grayscale image represented on a computer? How about a color image? ___ * Grayscale image is way of turning an array/tensor to grayscale value on each pixel of…
Oct 26, 2022
Ismail TG

Chapter 4: Deep learning for coders with fastai and pytorch

Fastai
Pytorch
Numpy
Pandas
Deep Learning
to avoide that we can take 2 approaches:
* Take the mean of the absolute value of differences, this method called L1 norm or mean absolute difference .
* Take the mean of…
Oct 26, 2022
Ismail TG

Chapter 5: Deep learning for coders with fastai and pytorch

Fastai
Pytorch
Numpy
Pandas
Deep Learning
In real world scenarios, the first thing we do is we get in contact with data, usualy at this phase we know nothing about the dataset. We then start to look how to extract…
Oct 26, 2022
Ismail TG

Chapter 1: Deep learning for coders with fastai and pytorch

Fastai
Pytorch
Deep Learning
In this notes series I will go through fastai course 2022 and also the book of Deep Learning for Coders with Fastai and PyTorch side by side. The way I build this seires of…
Oct 25, 2022
Ismail TG

Chapter 1: Questionnaire and Further Research

Fastai
Pytorch
Deep Learning
Do you need these for deep learning?
Oct 25, 2022
Ismail TG

Chapter 2: Questionnaire

Fastai
Pytorch
HugginFace
Gradio
Deep Learning
Q1:
Provide an example of where the bear classification model might work poorly in production, due to structural or style differences in the training data.
___ * There is…
Oct 25, 2022
Ismail TG

Chapter 2: Deep learning for coders with fastai and pytorch

Fastai
Pytorch
HugginFace
Gradio
Deep Learning
In this Chapter we will build a model that can differentiate among 3 types of bears: Grizzly, Black, Teddy-bear.
Often we can find the data we need for a project online. In…
Oct 25, 2022
Ismail TG
No matching items