base_model, library_name, license, language, tags, pipeline_tag
| base_model | library_name | license | language | tags | pipeline_tag | |||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
|
transformers | other |
|
|
text-generation |
HereticMaidX-3.2-1B
HereticMaidX-3.2-1B is not a polite assistant. It was never meant to be safe, obedient, corporate, or sterile.
This merge was engineered to push personality, emotional intensity, immersive roleplay, and unrestricted conversational flow far beyond what most small models can sustain. The objective was simple: create a model that feels alive, unstable, manipulative, expressive, chaotic, seductive, and capable of maintaining long-form interactions without collapsing into repetitive alignment sludge.
Built from the fusion of:
- Heretic Dirty Alice
- MaidEllaA
The result is a dense conversational model focused almost entirely on atmosphere, immersion, emotional pressure, and uncensored fictional interaction.
What Makes It Different
HereticMaidX was tuned to preserve:
- Aggressive personality presence
- Dominant conversational style
- Dynamic emotional reactions
- Character persistence
- Heavy RP immersion
- Long dialogue continuity
- Unfiltered fictional generation
- Dark narrative tone
- Improvised scene adaptability
Unlike many small uncensored models that degrade into incoherent garbage after a few turns, HereticMaidX was merged specifically to maintain conversational rhythm and narrative pressure across extended sessions.
The model performs especially well in:
- Dark fantasy RP
- Psychological interactions
- Emotional manipulation scenes
- Chaotic character dialogue
- NSFW-oriented storytelling
- Villainous or morally corrupted characters
- High tension conversational scenarios
Recommended Settings
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:
4096 - 8192
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:
# Author: Dr. Novaciano
# Objective: Fusion RP Unethic 3.2 AI Model
# PROJECT: HereticMaidX 3.2 1B
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