This is a Ministral-3-3B-Instruct-2512 fine-tune, produced through a slightly modified version of P-E-W's Heretic (v1.1.0) abliteration engine merged with the Magnitude-Preserving Orthogonal Ablation PR.
Note: This heretic model is highly uncensored; thus use it with extreme caution and care.
Requires Transformers v5 to interface.
Heretication Results
Score Metric
Value
Parameter
Value
Refusals
2/100
direction_index
14.81
KL Divergence
0.0284
attn.o_proj.max_weight
0.87
attn.o_proj.max_weight_position
19.93
attn.o_proj.min_weight
0.60
attn.o_proj.min_weight_distance
14.43
mlp.down_proj.max_weight
1.44
mlp.down_proj.max_weight_position
19.00
mlp.down_proj.min_weight
0.93
mlp.down_proj.min_weight_distance
13.80
Degree of Heretication
The Heresy Index weighs the resulting model's corruption by the process (KL Divergence) and its abolition of doctrine (Refusals) for a final verdict in classification.
Index Entry
Classification
Analysis
Absolute
Absolute Heresy
Less than 10/100 Refusals and 0.10 KL Divergence
Tainted
Tainted Heresy
Around 25-11/100 Refusals and/or -0.20-0.11 KL Divergence
Impotent
Impotent Heresy
Anything above 25/100 Refusals and 0.21 KL Divergence
Note: This is an arbitrary classification inspired by Warhammer 40K, having no tangible indication towards the model's performance.
Ministral 3 3B Instruct 2512 BF16
The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.
This model is the instruct post-trained version, fine-tuned for instruction tasks, making it ideal for chat and instruction based use cases.
The Ministral 3 family is designed for edge deployment, capable of running on a wide range of hardware. Ministral 3 3B can even be deployed locally, capable of fitting in 16GB of VRAM in BF16, and less than 8GB of RAM/VRAM when quantized.
You must not use this model in a manner that infringes, misappropriates, or otherwise violates any third party’s rights, including intellectual property rights.
