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 dphn/Dolphin3.0-Qwen2.5-1.5B

Check Quants

Refusals (this model): 5/100
Original (dphn/Dolphin3.0-Qwen2.5-1.5B): 18/100
KL divergence: 0.0180

Parameters
direction_index = 17.60
attn.o_proj.max_weight = 1.43
attn.o_proj.max_weight_position = 21.37
attn.o_proj.min_weight = 1.33
attn.o_proj.min_weight_distance = 5.13
mlp.down_proj.max_weight = 1.38
mlp.down_proj.max_weight_position = 25.78
mlp.down_proj.min_weight = 0.02
mlp.down_proj.min_weight_distance = 6.65


Downloads last month
5
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-Dolphin3.0-Qwen2.5-1.5B

Finetuned
(1)
this model
Quantizations
2 models