Gemma 3 abliterated

This is Gemma 3 4b with [abliteration technique] (https://www.lesswrong.com/posts/jGuXSZgv6qfdhMCuJ/refusal-in-llms-is-mediated-by-a-single-direction) applied to reduce refusals. (with high scale_factor=2.0 as it was very stubborn originally)

Tested its work in VLLM. It does give the disclaimers sometimes, but more or less often executes the instructions as needed, and the disclaimers are less aggressive.

Downloads last month
0
Safetensors
Model size
4.3B params
Tensor type
BF16
·
FP16
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for kabachuha/gemma3-4b-it-abliterated

Finetuned
(21)
this model