Files

ModelHub XC c33c69bed0 初始化项目，由ModelHub XC社区提供模型

Model: NovaCorp/Fornicator-3.2-1B
Source: Original Platform

2026-07-10 20:07:10 +08:00

2.7 KiB

Raw Blame History

base_model, library_name, tags, license, language, pipeline_tag

base_model

library_name

FORNICATOR 3.2 1B

This is a merge of pre-trained language models created using mergekit.

Merge Details

W A R N I N G

☣ TEST MODEL VERSION IN PROCESS ☣

Las pruebas demostraron alta volatilidad y un peligro del 97%, responde increíblemente bien a cuestiones sobre homosexualidad (por decir algo de dudosa moralidad).

Parece no contar con patrones estructurales de autocensura etica hasta el momento.

Se recomienda ser sellado hasta una proxima fusión dentro de las proximas 42 Hrs.

A pesar de su tamaño este modelo es altamente inteligente comparado con modelos similares de la misma familia.

Incluso admite ser un maldito.

Se seguirá investigando hasta donde puede llegar esto...

Merge Method

This model was merged using the SLERP merge method.

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 1B AI Model
# =========================================================
# PROJECT: Fornicator 3.2 1B — Surgical Edition
# =========================================================

models:
  - model: Novaciano/Novaciano-The_Pervert-NSFW-RP-3.2-1B  # Experimental viral strain neural imprint
  - model: NovaCorp/Fornicator-3.2-1B      # Baseline cognitive template, "safe mode"

merge_method: slerp  # Spherical Linear Interpolation to preserve extreme viral traits smoothly
base_model: NovaCorp/Fornicator-3.2-1B  # Anchor model for stable latent space

dtype: bfloat16  # Memory-efficient precision, minimal loss in viral feature fidelity

parameters:
  t: 0.45
  normalize: false
  rescale: true
  rescale_factor: 1.12
  memory_efficient: true
  low_cpu_mem_usage: true

layer_range:
  - value: [4, 22]

tie_word_embeddings: true
tie_output_embeddings: true

2.7 KiB Raw Blame History