GPT J 6B Janeway

🚀 GPT-J 6B - Janeway

A finetuned model based on EleutherAI's GPT-J 6B, trained on a diverse ebook dataset.

🚀 Quick Start

You can use this model directly with a pipeline for text generation. This example generates a different sequence each time it's run:

>>> from transformers import pipeline
>>> generator = pipeline('text-generation', model='KoboldAI/GPT-J-6B-Janeway')
>>> generator("Welcome Captain Janeway, I apologize for the delay.", do_sample=True, min_length=50)
[{'generated_text': 'Welcome Captain Janeway, I apologize for the delay."\nIt\'s all right," Janeway said. "I\'m certain that you\'re doing your best to keep me informed of what\'s going on."'}]

✨ Features

GPT-J 6B-Janeway is a finetune created using EleutherAI's GPT-J 6B model. The training data contains around 2210 ebooks, mostly in the sci-fi and fantasy genres. The dataset is based on the same dataset used by GPT-Neo-2.7B-Picard, with 20% more data in various genres. Some parts of the dataset have been prepended using the following text: [Genre: <genre1>,<genre2>]

📦 Installation

No specific installation steps were provided in the original document.

💻 Usage Examples

Basic Usage

>>> from transformers import pipeline
>>> generator = pipeline('text-generation', model='KoboldAI/GPT-J-6B-Janeway')
>>> generator("Welcome Captain Janeway, I apologize for the delay.", do_sample=True, min_length=50)
[{'generated_text': 'Welcome Captain Janeway, I apologize for the delay."\nIt\'s all right," Janeway said. "I\'m certain that you\'re doing your best to keep me informed of what\'s going on."'}]

📚 Documentation

Limitations and Biases

The core functionality of GPT-J is taking a string of text and predicting the next token. While language models are widely used for tasks other than this, there are a lot of unknowns with this work. When prompting GPT-J it is important to remember that the statistically most likely next token is often not the token that produces the most "accurate" text. Never depend upon GPT-J to produce factually accurate output.

GPT-J was trained on the Pile, a dataset known to contain profanity, lewd, and otherwise abrasive language. Depending upon use case GPT-J may produce socially unacceptable text. See Sections 5 and 6 of the Pile paper for a more detailed analysis of the biases in the Pile.

As with all language models, it is hard to predict in advance how GPT-J will respond to particular prompts and offensive content may occur without warning. We recommend having a human curate or filter the outputs before releasing them, both to censor undesirable content and to improve the quality of the results.

BibTeX entry and citation info

The model uses the following model as base:

@misc{gpt-j,
  author = {Wang, Ben and Komatsuzaki, Aran},
  title = {{GPT-J-6B: A 6 Billion Parameter Autoregressive Language Model}},
  howpublished = {\url{https://github.com/kingoflolz/mesh-transformer-jax}},
  year = 2021,
  month = May
}

🔧 Technical Details

The training data contains around 2210 ebooks, mostly in the sci-fi and fantasy genres. The dataset is based on the same dataset used by GPT-Neo-2.7B-Picard, with 20% more data in various genres. Some parts of the dataset have been prepended using the following text: [Genre: <genre1>,<genre2>]

📄 License

This project is licensed under the MIT license.

Acknowledgements

This project would not have been possible without compute generously provided by Google through the TPU Research Cloud, as well as the Cloud TPU team for providing early access to the Cloud TPU VM Alpha.