metadata

base_model:
  - cognitivecomputations/Dolphin-Mistral-24B-Venice-Edition
  - Gryphe/Pantheon-RP-1.8-24b-Small-3.1
  - aixonlab/Eurydice-24b-v3
  - ReadyArt/Omega-Darker_The-Final-Directive-24B
  - ReadyArt/Forgotten-Safeword-24B-v4.0
library_name: transformers
tags:
  - mergekit
  - merge
new_version: yvvki/Erotophobia-24B-v1.1

DO NOT USE

Totally borked for my first merge, I'll research on whats wrong. ~~Feel free to give some insight!~~

I totally did test the model first this time, hopefully it goes well here: https://huggingface.co/yvvki/Erotophobia-24B-v1.1

Erotophobia-24B-v1.0

My first merge and model ever! Literally depraved.

Heavily inspired by FlareRebellion/DarkHazard-v1.3-24b.

Quants

Thanks for mradermacer for providing the static GGUF quants here:
https://huggingface.co/mradermacher/Erotophobia-24B-v1.0-GGUF

Merge Details

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

Merge Method

This model was merged using the DARE TIES merge method using cognitivecomputations/Dolphin-Mistral-24B-Venice-Edition as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

base_model: cognitivecomputations/Dolphin-Mistral-24B-Venice-Edition
tokenizer:
  source: base
dtype: bfloat16
merge_method: dare_ties
parameters:
  normalize: true
models:
  - model: cognitivecomputations/Dolphin-Mistral-24B-Venice-Edition # uncensored
  - model: Gryphe/Pantheon-RP-1.8-24b-Small-3.1 # personality
    parameters:
      density: 0.5
      weight: 0.3
  - model: aixonlab/Eurydice-24b-v3 # creativity & storytelling
    parameters:
      density: 0.5
      weight: 0.3
  - model: ReadyArt/Omega-Darker_The-Final-Directive-24B # unhinged
    parameters:
      density: 0.65
      weight: 0.2
  - model: ReadyArt/Forgotten-Safeword-24B-v4.0 # lube
    parameters:
      density: 0.35
      weight: 0.2