Just gonna drop this link here for anyone who’s interested in a 3rd party Jellyfin user management application. This fixes the issues related to inviting users and allowing them to reset their own passwords. Would obviously prefer all of this built into jellyfin, but solutions do exist for those determined enough.

This is the answer. Not sure why everyone in the comments is discussing disassembly when turning the platters to dust in a couple hard smacks is fast and effective.

Running it offline does avoid some of the censorship, but not all. Let me explain: Failsafes are implimented to check what topics are being talked about (like tieneman square). These are not included inside the model itself (though it does have a type of post-training, reinforcement-based censorship applied to the finished model). This second type of censorship (the kind actually included in the model weights) can actually be removed by retraining using similar reinforcement techniques. This means that the Tldr is: There is censorship baked into the model but because the weights are public, it can be removed /bypassed. In contrast the deepseek web app includes both kinds of censorship (and also definitely steals your data). The local model obviously does not.