9 Downloads Updated yesterday
uncensored GLM Air
tools
thinking
Models
View all →Readme
Merged the split GGUFs
Our goal with this release is to provide a version of the model that removed refusal behaviors while maintaining the high-performance reasoning of the original GLM-4.5-Air. This is unlike regular abliteration which often inadvertently "lobotomizes" the model.
Methodology: Norm-Preserving Biprojected Abliteration
To achieve this, Arli AI utilized Norm-Preserving Biprojected Abliteration, a refined technique pioneered by Jim Lai (grimjim)
source: https://huggingface.co/mradermacher/GLM-4.5-Air-Derestricted-GGUF original model https://huggingface.co/ArliAI/GLM-4.5-Air-Derestricted