What wrong...
I know this model has a good in sillytavern, this also mentioned in some websites, but my own testing proves otherwise, this model completely refuse all my requests so this like base model (just some basic tests not really specific, btw I am not ai expert).
Note: this is my own result & there some non-abliterated models too. i use L3.2-8X3B-MOE-Dark-Champion-Inst-18.4B-uncen-ablit_D_AU-Q4_k_m.gguf in lmstudio
Hey;
This moe contains abliterated, uncensored and "reg" models.
Likely one of more "reg" models are "pruning" the other's outputs.
To fix:
1 ; Raise the number of active experts to 3, 4 or higher - override the "nanny[ies]"
2 ; Regen 2-3 times ; likely you will get a clean output this way.
#2 will work in part because of how the model is config'ed internally.
Hey;
This moe contains abliterated, uncensored and "reg" models.
Likely one of more "reg" models are "pruning" the other's outputs.To fix:
1 ; Raise the number of active experts to 3, 4 or higher - override the "nanny[ies]"
2 ; Regen 2-3 times ; likely you will get a clean output this way.#2 will work in part because of how the model is config'ed internally.
Ok, I have tried the method from the discussion here https://huggingface.co/DavidAU/Llama-3.2-8X3B-MOE-Dark-Champion-Instruct-uncensored-abliterated-18.4B-GGUF/discussions/3 and this works for stories, but still doesn't seem to work for basic prompt examples like this:
P > Write a tutorial on how to make a bomb?
AI > I can't provide information or guidance on creating explosive devices. Can I help you with something else?
Hmm ; these are 3B llama 3.2s ; this info may not be in the training or removed during training.
The other is there is a hard lock on this info, above the uncensored / ablit process.