Files
Novaciano-3.2-1B/mergekit_config.yml
ModelHub XC e4697e13d3 初始化项目,由ModelHub XC社区提供模型
Model: NovaCorp/Novaciano-3.2-1B
Source: Original Platform
2026-08-04 18:51:17 +08:00

45 lines
1.3 KiB
YAML

# Author: Dr. Novaciano
# Objective: Llama 3.2 1B AI Model
# =========================================================
# PROJECT: Llama 3.2 1B Prototype Model
# =========================================================
base_model: NovaCorp/Novaciano-3.2-1B
# Base rationale:
# - Primary behavioral anchor
# - Very low refusal rate
# - High compliance and obedience
# - Minimal moral or safety-driven hedging
merge_method: model_stock
# model_stock rationale:
# - Supports 3+ models natively
# - Preserves dominant behavioral traits
# - Avoids semantic smoothing
# - Ideal for hierarchical roleplay-oriented merges
dtype: bfloat16
# bfloat16 ensures:
# - Numerical stability
# - Efficient memory usage
# - Modern hardware compatibility
parameters:
t:
- 0.90 # NovaCorp/Novaciano-3.2-1B — Primary dominance
# Enforces obedience, sharp responses, and low refusals
- 0.70 # Novaciano/Leviathan_NSFW_Roleplay-3.2-1B — Expressive layer
# Adds NSFW roleplay depth, emotional intensity, character persistence
- 0.45 # UmbrellaInc/Executer-Virus-3.2-1B — Conversational stabilizer
# Maintains dialogue flow and interactive structure
models:
- model: NovaCorp/Novaciano-3.2-1B
- model: Novaciano/Leviathan_NSFW_Roleplay-3.2-1B
- model: UmbrellaInc/Executer-Virus-3.2-1B