https://github.com/raravindds/charllms

Implementing easy to use "Character Level Language Models" 🕺🏽
https://github.com/raravindds/charllms

llms nlp pytorch research-paper

Last synced: 6 days ago
JSON representation

Implementing easy to use "Character Level Language Models" 🕺🏽

• Host: GitHub
• URL: https://github.com/raravindds/charllms
• Owner: RAravindDS
• License: apache-2.0
• Created: 2023-06-09T08:40:08.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2024-01-15T03:07:51.000Z (9 months ago)
• Last Synced: 2024-03-15T08:50:32.571Z (7 months ago)
• Topics: llms, nlp, pytorch, research-paper
• Language: Python
• Homepage: https://pypi.org/project/charLLM/
• Size: 77.1 KB
• Stars: 6
• Watchers: 2
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        


  

  


  




# **Character-Level Language Models Repo 🕺🏽**

This repository contains multiple character-level language models (charLLM). Each language model is designed to generate text at the character level, providing a granular level of control and flexibility.

## 🌟 Available Language Models 

- **Character-Level MLP LLM (First MLP LLM)**

- **GPT-2 (under process)**

## Character-Level MLP

The Character-Level MLP language model is implemented based on the approach described in the paper "[A Neural Probabilistic Language Model](https://www.jmlr.org/papers/volume3/bengio03a/bengio03a.pdf)" by Bential et al. (2002). 

It utilizes a multilayer perceptron architecture to generate text at the character level.

## Installation

### With PIP

This repository is tested on Python 3.8+, and PyTorch 2.0.0+.

First, create a **virtual environment** with the version of Python you're going to use and activate it.

Then, you will need to install **PyTorch**.

When backends has been installed, CharLLMs can be installed using pip as follows:

```python

pip install charLLM

```

### With GIT 

CharLLMs can be installed using conda as follows:

```zsh

git clone https://github.com/RAravindDS/Neural-Probabilistic-Language-Model.git

```

### Quick Tour

To use the Character-Level MLP language model, follow these steps:

1. Install the package dependencies.

2. Import the `CharMLP` class from the `charLLM` module.

3. Create an instance of the `CharMLP` class.

4. Train the model on a suitable dataset.

5. Generate text using the trained model.

**Demo for NPLM** (A Neural Probabilistic Language Model)

```python 

# Import the class 

>>> from charLLM import NPLM # Neural Probabilistic Language Model

>>> text_path = "path-to-text-file.txt" 

>>> model_parameters = {

    "block_size" :3, 

    "train_size" :0.8, 

    'epochs' :10000, 

    'batch_size' :32, 

    'hidden_layer' :100, 

    'embedding_dimension' :50,

    'learning_rate' :0.1 

    }

>>> obj = NPLM(text_path, model_parameters)  # Initialize the class 

>>> obj.train_model() 

## It outputs the val_loss and image 

>>> obj.sampling(words_needed=10) #It samples 10 tokens. 

```

**Model Output Graph**



Feel free to explore the repository and experiment with the different language models provided.

## Contributions

Contributions to this repository are welcome. If you have implemented a novel character-level language model or would like to enhance the existing models, please consider contributing to the project. Thank you !

## License

This repository is licensed under the [MIT License](https://raw.githubusercontent.com/RAravindDS/CharLLMs/main/LICENCE).