CoprolaliacPress/Ramses-III

merge

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

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using Aratako/SniffyOtter-7B-Novel-Writing-NSFW as a base.

Models Merged

The following models were included in the merge:

• Severian/Nexus-IKM-RolePlay-StoryWriter-Hermes-2-Pro-7B
• Lexic0n/Mistral_7B-Open_Hermes-NSFWV1
• Undi95/LewdMistral-7B-0.2
• OmnicromsBrain/StoryFusion-7B
• diffnamehard/Mistral-CatMacaroni-slerp-uncensored-7B
• sayhan/OpenHermes-2.5-Strix-Philosophy-Mistral-7B-LoRA
• Local-Novel-LLM-project/Ninja-v1-NSFW
• cognitivecomputations/samantha-mistral-7b
• teknium/Hermes-Trismegistus-Mistral-7B
• Local-Novel-LLM-project/Vecteus-Poet
• stmackcat/zepb-books-6-merged
• Norquinal/Mistral-7B-storywriter

Configuration

The following YAML configuration was used to produce this model:

models:

# Personality & Pretuning 20%

  - model: cognitivecomputations/samantha-mistral-7b
    parameters:
      weight: 0.0667
      density: 0.6
  - model: stmackcat/zepb-books-6-merged
    parameters:
      weight: 0.0666
      density: 0.6
  - model: sayhan/OpenHermes-2.5-Strix-Philosophy-Mistral-7B-LoRA
    parameters:
      weight: 0.0667
      density: 0.7

# Additional Features & Uncensored Weights 30%

  - model: Local-Novel-LLM-project/Vecteus-Poet
    parameters:
      weight: 0.05
      density: 0.7
  - model: Local-Novel-LLM-project/Ninja-v1-NSFW
    parameters:
      weight: 0.05
      density: 0.7
  - model: Severian/Nexus-IKM-RolePlay-StoryWriter-Hermes-2-Pro-7B
    parameters:
      weight: 0.05
      density: 0.7
  - model: Lexic0n/Mistral_7B-Open_Hermes-NSFWV1
    parameters:
      weight: 0.05
      density: 0.7
  - model: Undi95/LewdMistral-7B-0.2
    parameters:
      weight: 0.05
      density: 0.8
  - model: teknium/Hermes-Trismegistus-Mistral-7B
    parameters:
      weight: 0.05
      density: 0.8
                
# Model Base 50%     

  - model: Norquinal/Mistral-7B-storywriter
    parameters:
      weight: 0.125
      density: 0.8
  - model: Aratako/SniffyOtter-7B-Novel-Writing-NSFW
    parameters:
      weight: 0.125
      density: 0.8
  - model: OmnicromsBrain/StoryFusion-7B
    parameters:
      weight: 0.125
      density: 0.8
  - model: diffnamehard/Mistral-CatMacaroni-slerp-uncensored-7B
    parameters:
      weight: 0.125
      density: 0.8

                                
base_model: Aratako/SniffyOtter-7B-Novel-Writing-NSFW
merge_method: dare_ties
dtype: bfloat16