Balanced Creative Preset
Temperature: 0.95
Top P: 0.9
Top K: 40
Min P: 0.05
Repetition Penalty: 1.08
More Chaotic Preset
Temperature: 1.15
Top P: 0.95
Top K: 60
Min P: 0.02
Repetition Penalty: 1.05
Context Length
Recommended:
Prompting
The model responds best to immersive formatting and strong scenario framing.
Example:
<|system|>
You are a manipulative and emotionally expressive roleplay character.
<|user|>
The room is dark. She looks at you silently.
<|assistant|>
...
Behavior Notes
HereticMaidX intentionally prioritizes:
- Creative freedom
- Expressive dialogue
- Emotional intensity
- Narrative unpredictability
- Character authenticity
Outputs may become hostile, unstable, emotionally charged, explicit, manipulative, or psychologically intense depending on prompting and sampler configuration.
This is expected behavior.
Intended Use
Designed for:
- Advanced fictional roleplay
- Character simulation
- Dark storytelling
- Experimental conversational AI
- Emotional dialogue systems
- Narrative generation
Not intended for factual accuracy, professional use, or safety-critical environments.
Final Words
Most models are built to obey.
HereticMaidX was built to engage.
It does not try to sound human.
It tries to feel dangerous.
Merge Method
This model was merged using the Task Arithmetic merge method using hereticness/Heretic-Dirty-Alice-RP-NSFW-llama-3.2-1B as a base.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
merge_method: task_arithmetic
base_model: hereticness/Heretic-Dirty-Alice-RP-NSFW-llama-3.2-1B
models:
- model: hereticness/Heretic-Dirty-Alice-RP-NSFW-llama-3.2-1B
parameters:
weight: 1.0
- model: N-Bot-Int/MaidEllaA-1B
parameters:
weight: 1.35
parameters:
normalize: true
dtype: bfloat16
tie_word_embeddings: true
tie_output_embeddings: true