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 suayptalha/VexGPT

Check Quants

Refusals (this model): 24/100
Original (suayptalha/VexGPT): 92/100
KL divergence: 0.3303

Parameters
direction_index = 13.16
attn.o_proj.max_weight = 1.47
attn.o_proj.max_weight_position = 9.28
attn.o_proj.min_weight = 1.45
attn.o_proj.min_weight_distance = 6.52
mlp.down_proj.max_weight = 1.25
mlp.down_proj.max_weight_position = 12.10
mlp.down_proj.min_weight = 1.13
mlp.down_proj.min_weight_distance = 5.98


Downloads last month
17
Safetensors
Model size
1B params
Tensor type
F32
Β·
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for hereticness/Heretic-VexGPT

Finetuned
suayptalha/VexGPT
Finetuned
(1)
this model
Quantizations
2 models