726 Downloads Updated 1 year ago
WizardLM 2 7b Abliterated, fine tuned and uncensored
Models
View all →Readme
This is abliterated and further fine tuned to be uncensored.
This is a version of WizardLM-2-7B using the orthogonalization process implemented at: https://huggingface.co/failspy/llama-3-70B-Instruct-abliterated/blob/main/ortho_cookbook.ipynb
Finetuned using Datasets
https://huggingface.co/datasets/NobodyExistsOnTheInternet/ToxicQAFinal
It appears to work well but it still refuses some questions. Jailbreaking will improve this.
Source: https://huggingface.co/fearlessdots/Alpha-Orionis-v0.1-GGUF