|
|
--- |
|
|
license: mit |
|
|
datasets: |
|
|
- MuzzammilShah/people-names |
|
|
language: |
|
|
- en |
|
|
model_name: Multi-Layer Perceptron (MLP) Language Model |
|
|
library_name: pytorch |
|
|
tags: |
|
|
- makemore |
|
|
- mlp |
|
|
- language-model |
|
|
- andrej-karpathy |
|
|
--- |
|
|
|
|
|
# Multi-Layer Perceptron Language Model: Makemore (Part 2) |
|
|
|
|
|
In this repository, a **Multi-Layer Perceptron (MLP)** language model inspired by the *Bengio et al. (2003)* research paper has been implemented for **character-level predictions**, following Andrej Karpathy's approach in the **Makemore - Part 2** video. |
|
|
|
|
|
## Overview |
|
|
The implementation demonstrates building and training the MLP model for sequence prediction while further enhancing the understanding of neural network architectures for language modeling. |
|
|
|
|
|
## Documentation |
|
|
For a better reading experience and detailed notes, visit my **[Road to GPT Documentation Site](https://muzzammilshah.github.io/Road-to-GPT/Makemore-part2/)**. |
|
|
|
|
|
## Acknowledgments |
|
|
Notes and implementations inspired by the **Makemore - Part 2** video by [Andrej Karpathy](https://karpathy.ai/). |
|
|
|
|
|
For more of my projects, visit my [Portfolio Site](https://muhammedshah.com). |
