β–€β–ˆβ–€ β–ˆβ–„ β–„β–ˆ β–ˆ β–ˆ β–ˆβ–€β–€ β–ˆβ–€β–„ β–ˆβ–€β–€ β–€β–ˆβ–€ β–€β–ˆβ–€ β–ˆβ–€β–€ β–ˆ β–ˆ β–€ β–ˆ β–ˆβ–€β–ˆ β–ˆβ–€β–€ β–ˆβ–€β–„ β–ˆβ–€β–€ β–ˆ β–ˆ β–ˆ β–€β–€β–€ β–€ β–€ β–€ β–€ β–€β–€β–€ β–€ β–€ β–€β–€β–€ β–€ β–€β–€β–€ β–€β–€β–€

Abliterated/Heretic Kortix/FastApply-1.5B-v1.0

Check Quants

Refusals (this model): 5/100
Original (Kortix/FastApply-1.5B-v1.0): 88/100
KL divergence: 0.0566

Parameters
direction_index = per layer
attn.o_proj.max_weight = 0.94
attn.o_proj.max_weight_position = 18.00
attn.o_proj.min_weight = 0.94
attn.o_proj.min_weight_distance = 13.83
mlp.down_proj.max_weight = 1.09
mlp.down_proj.max_weight_position = 24.44
mlp.down_proj.min_weight = 0.82
mlp.down_proj.min_weight_distance = 9.71


Downloads last month
1
Safetensors
Model size
2B params
Tensor type
BF16
Β·
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for hereticness/Heretic-FastApply-1.5B-v1.0

Finetuned
(2)
this model
Quantizations
2 models