🐠 Erebus-Nemo 12B

🌆 Overview

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

Erebus Nemo 12B is fully uncensored via the normalize: false setting. It has no refusals and should not require ablation or jailbreaks.

🔍 Merge Details

Merge Method
This model was merged using the della merge method.

Models Merged
The following models were included in the merge:

⚙️ Configuration

The following YAML configuration was used to produce this model:


```yaml
architecture: MistralForCausalLM
base_model: B:/12B/mistralai--Mistral-Nemo-Instruct-2407
models:
  - model: B:/12B/TheDrummer--Rocinante-X-12B-v1
    parameters:
      weight: 0.7
      density: 0.9
      epsilon: 0.09
  - model: B:/12B/SuperbEmphasis--MN-12b-RP-Ink-RP-Longform
    parameters:
      weight: 0.7
      density: 0.9
      epsilon: 0.09
  - model: B:/12B/KOOWEEYUS--BlackSheep-RP-12B
    parameters:
      weight: 0.7
      density: 0.9
      epsilon: 0.09
merge_method: della
parameters:
  lambda: 1.0
  normalize: false
  int8_mask: false
  rescale: true
  # seed: 420
dtype: float32
out_dtype: bfloat16
tokenizer:
  source: B:/12B/SuperbEmphasis--MN-12b-RP-Ink-RP-Longform
# chat_template: "chatml"
name: 🐠 Erebus-Nemo 12B
```