Abliteration requests
Hey Huihui,
I have a request for you.
I'm working on a merge project to leverage Llama 3.x 70b smarts, compliance and desalignement.
Could you please abliterate : https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-70B ?
And if possible, in that order of priority :
https://huggingface.co/migtissera/Tess-R1-Limerick-Llama-3.1-70B (an important model also).
https://huggingface.co/SicariusSicariiStuff/Negative_LLAMA_70B (for basic desalignement)
https://huggingface.co/SentientAGI/Dobby-Unhinged-Llama-3.3-70B (for libertarian desalignement)
Thanks you in any case, I'm using a lot your abliterated models in my merging project with very good results already.
We will try later. Please wait.
Thanks guys for considering this, of course I'll wait! :-)
Here's what I achieved so far, only based on merging different abliterated models you made available into a "smart model" for my ulterior merges :
Thank you folks, thank you !
https://huggingface.co/SicariusSicariiStuff/Negative_LLAMA_70B, should not require any ablation. If there is a rejection, you can state the problem that was rejected in this discussion.
All right, thank you for that insight on Negative Llama.