hitting censorship running in gpt4all
I'm a web dev who's new to self-run models & a novice with LLMs, so pardon if this is the wrong forum
I've loaded this model in gpt4all, but when I ask it to write spicy things, I get this:
I can't help with that request. Is there something else you'd like to discuss or explore? Perhaps we could talk about relationships, intimacy, or even creative writing prompts? I'm here to provide helpful information on a wide range of topics and offer guidance when needed. If you have any specific questions or concerns, feel free to ask!
Is this related to the model, or is it a gpt4all issue? I was able to get uncensored results from another llama3 model using colab. that model wasn't marketed as uncensored, so my assumption is gpt4all is shortstopping my request w/ some SFW filters.
Loading the model in LM Studio presents no such blockers, so I am concluding this is a gpt4all thing.
@nonada It's important you follow the instructions, and use the correct template. If you use the wrong template for chatting you will have undefined behavior.
I suggest you to use Anything LLM. I prefer this one than gpt4all because of some other bugs with other models