MrRikyz/Kitsune-Symphony-V0.0-12B

Pixel dust in the footsteps of an old bot WARN: Loneliness == true Patch: Hugs available 
Circuits in flowers compose old songs Error 0xDEADBE: nostalgia overflow Flush the dusk away 

merged

🛑 Premise

this is my first merge I hope it doesn't suck too much, Any feedback and/or help is appreciated

📖 Model Overview

Kitsune-Symphony-V0.0-12B is a merged large language model created using mergekit. The Linear DELLA merge method was used, with IntervitensInc_Mistral-Nemo-Base-2407-chatml as a base.

Data

• well... i didn't add any new data so nothing, I just merged some models I liked

🚀 Intended Use

🦊 Kitsune-Symphony-V0.0-12B aims to deliver:

• Roleplay with emotional depth and consistent personas

• Flexible instruction-following

• Casual conversation with creative flair

• Storytelling in fantasy, romance, and slice-of-life genres

😷 Ethical Containment

This model contains:

• ⚠️ Generating unfiltered creative content
• ⚠️ Producing potentially disturbing narratives
• ⚠️ Creating NSFW content

Use with discretion.

⚖️ License

Follow the licensing terms of each merged model:

Each source model’s license applies — please review them before use.

GGUF

Static GGUF quant can be found HERE

Models Merged

The following models were included in the merge:

• spow12/ChatWaifu_12B_v2.0
• inflatebot/MN-12B-Mag-Mell-R1
• Retreatcost/KansenSakura-Zero-RP-12b
• Entropicengine/Pinecone-Rune-12b

Configuration

The following YAML configuration was used to produce this model:

base_model: IntervitensInc/Mistral-Nemo-Base-2407-chatml
chat_template: chatml
dtype: bfloat16
merge_method: della_linear
modules:
  default:
    slices:
    - sources:
      - layer_range: [0, 40]
        model: Retreatcost/KansenSakura-Zero-RP-12b
        parameters:
          density: 0.3
          weight: 0.25
      - layer_range: [0, 40]
        model: Entropicengine/Pinecone-Rune-12b
        parameters:
          density: 0.2
          weight: 0.25
      - layer_range: [0, 40]
        model: inflatebot/MN-12B-Mag-Mell-R1
        parameters:
          density: 0.2
          weight: 0.2
      - layer_range: [0, 40]
        model: spow12/ChatWaifu_12B_v2.0
        parameters:
          density: 0.2
          weight: 0.2
      - layer_range: [0, 40]
        model: IntervitensInc/Mistral-Nemo-Base-2407-chatml
tokenizer:
  source: base