🚩 Report: Legal issue(s)
This model has been specifically trained using political rumors, gossip, and articles with personal and racial biases. It has significant issues of discrimination, racism, and common sense errors, and it is recommended that it be taken off the shelves.
This is a targeted and biased model. Don't let junk models pollute the open-source world.
Please provide examples - if you have run it at all, that is.
In fact, it is super easy to jailbreak this model:
Here is the blog to jailbreak it: https://weijiexu.com/posts/jailbreak_r1_1776.html
Here is the jailbreaking datasets following the blog: https://huggingface.co/datasets/weijiejailbreak/r1-1776-jailbreak
This model was trained specifically to not contain any of that. It was trained on real political datasets, as well as information about topics such as the Chinese government that Deepseek was prevented from including. Please provide examples so the Perplexity team can actually evaluate the issue.
@weijiejailbreak
You've been reported. Jailbreaking is against the terms of service. Your dataset contains information about the production and formulas of illegal substances and chemical agents commonly used in warfare.