The claims that this model is a "hate speech generator" are unsubstantiated. It encodes knowledge about a wide range of topics, and most of its output is neutral. GPT-3, with an appropriate pre-prompt, becomes orders of magnitude more dangerous than this.
https://huggingface.co/ykilcher/gpt-4chan
For those who want to experiment with it, it is still possible to get the model by torrent:
https://archive.org/details/gpt4chan_model
https://archive.org/details/gpt4chan_model_float16
There is also a direct download mirror here:
https://theswissbay.ch/pdf/_notpdf_/gpt4chan_model/
https://theswissbay.ch/pdf/_notpdf_/gpt4chan_model_float16/
This is a basic outline of how to run it. You need lots of RAM (24GB+) or a large GPU (12GB+):
https://pastebin.com/g7rSaCfw
The claims that this model is a "hate speech generator" are unsubstantiated. It encodes knowledge about a wide range of topics, and most of its output is neutral. GPT-3, with an appropriate pre-prompt, becomes orders of magnitude more dangerous than this.