MuzzammilShah commited on
Commit
0f1c84d
·
verified ·
1 Parent(s): 0da3d0b

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +30 -55
README.md CHANGED
@@ -1,56 +1,31 @@
1
- ## SET 1 - MAKEMORE (PART 5) 🔗
2
-
3
- [![Documentation](https://img.shields.io/badge/Documentation-Available-blue)](https://muzzammilshah.github.io/Road-to-GPT/Makemore-part5/)
4
- ![Number of Commits](https://img.shields.io/github/commit-activity/m/MuzzammilShah/NeuralNetworks-LanguageModels-5?label=Commits)
5
- [![Last Commit](https://img.shields.io/github/last-commit/MuzzammilShah/NeuralNetworks-LanguageModels-5.svg?style=flat)](https://github.com/MuzzammilShah/NeuralNetworks-LanguageModels-5/commits/main)
6
- ![Project Status](https://img.shields.io/badge/Status-Done-success)
7
-
8
-  
9
-
10
- ### **Overview**
11
-
12
- We take the 2-layer MLP from previous video and make it deeper with a tree-like structure, arriving at a convolutional neural network architecture similar to the WaveNet (2016) from DeepMind. In the WaveNet paper, the same hierarchical architecture is implemented more efficiently using causal dilated convolutions (not yet covered). Along the way we get a better sense of `torch.nn` and what it is and how it works under the hood, and what a typical deep learning development process looks like.
13
-
14
-  
15
-
16
- ### **🗂️Repository Structure**
17
-
18
- ```plaintext
19
- ├── .gitignore
20
- ├── Main-notebook-part-5.ipynb
21
- ├── README.md
22
- ├── notes/
23
- │ ├── Main-makemore-part-5.md
24
- │ └── README.md
25
- └── names.txt
26
- ```
27
-
28
- - **Notes Directory**: Contains detailed notes corresponding to each notebook section.
29
- - **Jupyter Notebooks**: Step-by-step implementation and exploration of the concepts.
30
- - **README.md**: Overview and guide for this repository.
31
- - **names.txt**: Supplementary data file used in training the model.
32
-
33
-  
34
-
35
- ### **📄Instructions**
36
-
37
- To get the best understanding:
38
-
39
- 1. Start by reading the notes in the `notes/` directory. Each section corresponds to a notebook for step-by-step explanations.
40
- 2. Open the corresponding Jupyter Notebook.
41
- 3. Follow the code and comments for a deeper dive into the implementation details.
42
-
43
-  
44
-
45
- ### **⭐Documentation**
46
-
47
- For a better reading experience and detailed notes, visit my **[Road to GPT Documentation Site](https://muzzammilshah.github.io/Road-to-GPT/)**.
48
-
49
- > **💡Pro Tip**: This site provides an interactive and visually rich explanation of the notes and code. It is highly recommended you view this project from there.
50
-
51
-  
52
-
53
- ### **✍🏻Acknowledgments**
54
- Notes and implementations inspired by the **Makemore - Part 5** video by [Andrej Karpathy](https://karpathy.ai/).
55
-
56
  For more of my projects, visit my [Portfolio Site](https://muhammedshah.com).
 
1
+ ---
2
+ license: mit
3
+ datasets:
4
+ - MuzzammilShah/people-names
5
+ language:
6
+ - en
7
+ model_name: Deep MLP with WaveNet-inspired Architecture
8
+ library_name: pytorch
9
+ tags:
10
+ - makemore
11
+ - wavenet
12
+ - convolutional-neural-network
13
+ - deep-learning
14
+ - andrej-karpathy
15
+ ---
16
+
17
+ # Deep MLP with WaveNet-inspired Architecture: Makemore (Part 5)
18
+
19
+ This repository builds upon the 2-layer MLP from previous implementations, making it deeper with a tree-like structure, leading to a convolutional neural network architecture inspired by the WaveNet (2016) from DeepMind.
20
+
21
+ ## Overview
22
+ - This hierarchical architecture is implemented efficiently using causal dilated convolutions (not yet covered).
23
+ - The project explores `torch.nn` and its functionality, providing insights into deep learning development processes.
24
+
25
+ ## Documentation
26
+ For a better reading experience and detailed notes, visit my **[Road to GPT Documentation Site](https://muzzammilshah.github.io/Road-to-GPT/Makemore-part5/)**.
27
+
28
+ ## Acknowledgments
29
+ Notes and implementations inspired by the **Makemore - Part 5** video by [Andrej Karpathy](https://karpathy.ai/).
30
+
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
31
  For more of my projects, visit my [Portfolio Site](https://muhammedshah.com).