Request for a different model
Hi, sorry to shit up the discussions page, but could you try this on gemma 3 27b? I'd really like to see if it could be salvaged with this technique. It has really good world knowledge for its size and image analysis capabilities.
Not the 27b version you are asking for, but there are 12b versions...
https://huggingface.co/collections/grimjim/highlighted-work
good abliteration of gemma 27B is by mlabonne's. But first version, not second. At least worked for RP.
Out of curiosity, I wonder how would this method work with ServiceNow-AI/Apriel-1.5-15b-Thinker - that one puts GPT-OSS to shame when it comes to refusals, being ridiculously over-censored.
Would love to see a full model of the latest version with abliteration!
https://huggingface.co/zai-org/GLM-4.6