|
|
---
|
|
|
license: gpl-3.0
|
|
|
datasets:
|
|
|
- lmsys/lmsys-chat-1m
|
|
|
language:
|
|
|
- en
|
|
|
pipeline_tag: text-generation
|
|
|
---
|
|
|
|
|
|
<img src="ShaNet.png" alt="ShaNet Banner" width="100%">
|
|
|
|
|
|
# ShaNet
|
|
|
|
|
|
ShaNet is a Generative Pre-trained Transformer (GPT) trained on conversational data designed to understand and generate human-like text based on the input it receives. This model can be used for various applications such as chatbots, content generation, and more.
|
|
|
|
|
|
## Features
|
|
|
- **Conversational Understanding**: Trained on a diverse dataset to understand context and nuances in conversations.
|
|
|
- **Text Generation**: Capable of generating coherent and contextually relevant text.
|
|
|
- **Customizable**: Can be fine-tuned for specific applications or domains.
|
|
|
- **Open Source**: Available for use and modificatio under the permissive GPL-3.0 license.
|
|
|
|
|
|
## Installation
|
|
|
To install ShaNet, you can downlaod all files and run the `chat.py` script.
|
|
|
|
|
|
Note:
|
|
|
- The train and config code are modified versions of train.py and configurator.py from [NanoGPT](https://github.com/karpathy/nanoGPT). |
