Nemo-Instruct-2407-MPOA-v2-12B

MPOA (Magnitude-Preserving Othogonalized Ablation, AKA norm-preserving biprojected abliteration) has been applied the many of the layers in this model, to both mlp.down_proj.weight and self_attn.o_proj.weight streams.

Compliance was not maximized for this model. The model appears to be near an edge of chaos with regard to some safety refusals, which should be suitable for varied text completion.

More details pending.

Downloads last month
24
Safetensors
Model size
12B params
Tensor type
BF16
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for grimjim/Nemo-Instruct-2407-MPOA-v2-12B

Finetuned
(150)
this model
Finetunes
1 model
Quantizations
5 models