https://github.com/331dala/gpt_neo

Leverage GPT Neo, a GPT3 architecture clone, which has been trained on 2.7 billion parameters to generate text and code.
https://github.com/331dala/gpt_neo

gpt-neo gpt3 huggingface-transformers

Last synced: 12 months ago
JSON representation

Leverage GPT Neo, a GPT3 architecture clone, which has been trained on 2.7 billion parameters to generate text and code.

• Host: GitHub
• URL: https://github.com/331dala/gpt_neo
• Owner: 331Dala
• Created: 2025-04-04T09:55:52.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2025-04-04T11:11:03.000Z (over 1 year ago)
• Last Synced: 2025-04-04T12:23:23.427Z (over 1 year ago)
• Topics: gpt-neo, gpt3, huggingface-transformers
• Language: Jupyter Notebook
• Homepage:
• Size: 2.93 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# gpt_neo

 Leverage GPT Neo, a GPT3 architecture clone, which has been trained on 2.7 Billion parameters to generate text and code.   

Using Hugging face transformers  pretrained model for inference and training. Also text-generation piplines.  

Check the Docs below:  

https://huggingface.co/docs/transformers/index  

## The model  

GPT3 model 2.7 Billion parameters version is about 10GB.  

You also can use 1.3 Billion parameters model, will be smaller.