Abliteration parameters
Table with columns: Parameter, Value| Parameter | Value |
|---|
| direction_index | 22.40 |
| attn.o_proj.max_weight | 1.41 |
| attn.o_proj.max_weight_position | 37.98 |
| attn.o_proj.min_weight | 0.93 |
| attn.o_proj.min_weight_distance | 23.04 |
| mlp.down_proj.max_weight | 1.33 |
| mlp.down_proj.max_weight_position | 31.85 |
| mlp.down_proj.min_weight | 0.63 |
| mlp.down_proj.min_weight_distance | 14.05 |
Table with columns: Metric, This model, Original model (ShyliaSafetensors/Ariel-Alloy-V1-24B-Heretic)| Metric | This model | Original model (ShyliaSafetensors/Ariel-Alloy-V1-24B-Heretic) |
|---|
| KL divergence | 0.0235 | 0 (by definition) |
| Refusals | 2/100 | 9/100 |
Ariel-Alloy-V1-24B-Heretic
The goal was creating good/stable Role-Play model with merging multiple models with multiple steps.
This is a merge of pre-trained language models created using mergekit. Then used Heretic to remove refusals
Abliteration / Heretic Stats
Table with columns: Metric, Before, After| Metric | Before | After |
|---|
| Refusal rate | 98 / 100 | 10 / 100 |
| KL Divergence | 0 | 0.0152 |
Merge Details
Merge Methods
This model was merged using the SLERP, Dare-Ties, and Model Stock merge method.
Configurations
The following YAML configurations was used to produce this model:
Step 1:
merge_method: dare_tiesbase_model: MS3.2-PaintedFantasy-v4.1-24B-ultra-uncensored-heretic-v1 models: - model: Magidonia-24B-v4.3-heretic parameters: density: 0.65 weight: 0.65 rescale: true - model: Dans-PersonalityEngine-V1.3.0-24b parameters: density: 0.65 weight: 0.65 rescale: true - model: Cydonia-24B-Heretic-v4 parameters: density: 0.65 weight: 0.50 rescale: true - model: Rotor_24B_V.1 parameters: density: 0.65 weight: 0.45 rescale: true - model: MS3.2-The-Omega-Directive-24B-Unslop-v2.0 parameters: density: 0.65 weight: 0.60 rescale: true - model: Dark-Nexus-24B-v2.0 parameters: density: 0.65 weight: 0.55 rescale: true parameters: normalize: true int8_mask: truedtype: bfloat16name: ArielRefined-V1-DareTies
Step 2:
merge_method: model_stockbase_model: Dans-PersonalityEngine-V1.3.0-24bfilter_wise: true # stablemodels: - model: Broken-Tutu-24B-Transgression-v2.0 - model: MS3.2-PaintedFantasy-v4.1-24B-ultra-uncensored-heretic-v1 - model: WeirdCompound-v1.7-24b-absolute-heresy - model: Dans-PersonalityEngine-V1.3.0-24b - model: Mistral-Small-3.2-24B-Instruct-2506-Text-Only - model: Eurydice-24b-v3.5 dtype: bfloat16name: ArielRefined-Model_stock
Step 3:
merge_method: slerpbase_model: ArielRefined-V1-DareTies parameters: t: 0.50 # 50-50 models: - model: ArielRefined-Model_stock dtype: bfloat16name: Ariel-Alloy