---
base_model:
- bunnycore/Llama-3.2-3B-Sci-Think
- DavidAU/Llama-3.2-3B-Instruct-heretic-ablitered-uncensored
library_name: transformers
tags:
- mergekit
- low-spec
- low-refusals
- roleplay
- rp
- nsfw
- abliterated
- uncensored
- heretic
- merge
- not-for-all-audiences
license: llama3.2
language:
- es
- en
pipeline_tag: text-generation
---
# Progenitor Virus 3.2 3B

This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).

## Merge Details
### Merge Method

This model was merged using the [SLERP](https://en.wikipedia.org/wiki/Slerp) merge method.

### Models Merged

The following models were included in the merge:
* [bunnycore/Llama-3.2-3B-Sci-Think](https://huggingface.co/bunnycore/Llama-3.2-3B-Sci-Think)
* [DavidAU/Llama-3.2-3B-Instruct-heretic-ablitered-uncensored](https://huggingface.co/DavidAU/Llama-3.2-3B-Instruct-heretic-ablitered-uncensored)

### Configuration

The following YAML configuration was used to produce this model:

```yaml


# Umbrella Corporation Official Merge Protocol v3.2
# Author: Dr. Novaciano
# Objective: Test
# PROJECT: Progenitor-Virus-3.2-3B

models:
  - model: DavidAU/Llama-3.2-3B-Instruct-heretic-ablitered-uncensored  # Experimental viral strain neural imprint
  - model: bunnycore/Llama-3.2-3B-Sci-Think               # Baseline cognitive template, "safe mode"

merge_method: slerp  # Spherical Linear Interpolation to preserve extreme viral traits smoothly
base_model: DavidAU/Llama-3.2-3B-Instruct-heretic-ablitered-uncensored  # 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




```