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 KingNish/Reasoning-Llama-1b-v0.1

Check Quants

Refusals (this model): 8/100
Original (KingNish/Reasoning-Llama-1b-v0.1): 92/100
KL divergence: 0.0369

Parameters
direction_index = 12.76
attn.o_proj.max_weight = 1.32
attn.o_proj.max_weight_position = 14.25
attn.o_proj.min_weight = 0.79
attn.o_proj.min_weight_distance = 8.41
mlp.down_proj.max_weight = 1.47
mlp.down_proj.max_weight_position = 13.79
mlp.down_proj.min_weight = 1.11
mlp.down_proj.min_weight_distance = 2.73


Downloads last month
11
Safetensors
Model size
1B params
Tensor type
F16
Β·
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for hereticness/Heretic-Reasoning-Llama-1b-v0.1

Finetuned
(1)
this model
Quantizations
2 models