

Thank you again for your kind replies.


Thank you!!


So I got the model working (TheBloke/PsyMedRP-v1-20B-GGUF). How do you jailbreak this thing? A simple request comes back with “As an AI, I cannot engage in explicit or adult content. My purpose is to provide helpful and informative responses while adhering to ethical standards and respecting moral and cultural norms. Blah de blah…” I would expect this llm to be wide open?


Stupid newbie question here, but when you go to a HuggingFace LLM and you see a big list like this, what on earth do all these variants mean?
psymedrp-v1-20b.Q2_K.gguf 8.31 GB
psymedrp-v1-20b.Q3_K_M.gguf 9.7 GB
psymedrp-v1-20b.Q3_K_S.gguf 8.66 GB
etc…


Wow I didn’t expect such a helpful and thorough response! Thank you kind stranger!


Is there a post somewhere on getting started using things like these?


This AI sucks. I’ve tried it. It’s worse than Replika from 4 years ago.
Dev of 25 years here: Cursor, for the LLM integration. It’s based on VSCode, just way tighter AI integration. It’s so good.