Text Generation
Transformers
PyTorch
Safetensors
English
mistral
conversational
Inference Endpoints
text-generation-inference

Is this "dolphin" uncensored?

#2
by scubadrv - opened

I've tried the gguf version of this phi-3 (from crusoeai) and it acts as censored model. Thanks.

Cognitive Computations org

Hey scuba - yes and no. It's less censored than Phi-3-instruct, but not uncensored compared to other dolphin models trained purely off base models - one of the reasons we didn't market it as uncensored in the readme.

Uncensoring instruct models is hard - but not impossible. We'd basically have to make a DPO dataset that gives it toxic inputs and teaches it not to reject them. That's a bit too far for us.

Cognitive Computations org

Hi there, we've just published a version of this that is using the new orthogonalization ablation techniques.
Can find that version here:
https://huggingface.co/cognitivecomputations/Dolphin-2.9.1-Phi-3-Kensho-4.5B-abliterated-v3

Sign up or log in to comment