[!IMPORTANT] ⚠️ Warning: This model can produce narratives and RP that contain violent and graphic erotic content. Adjust your system prompt accordingly, and use Mistral Tekken chat template.

🚀 Cyberdonia 24B v8

🚀 Cyberdonia 24B v8

⚗️ The Alchemical Crucible 🔥

This is a merge of pre-trained language models created using mergekit-exp, a custom fork of the official mergekit. This model was merged using the della merge method.

The model is fully uncensored with 0 refusals despite not using any form of Heretic/ablation due to the un-normalized magnitude of the merge.

In my opinion this model produces superior writing to Cydonia-24B-v4.3-absolute-heresy. Several other variants were tested including swapping v4q in place of v4y, yet this produced inferior results.

Audit

v8
[DELLA Audit] Layer: model.layers.0.mlp.up_proj.weight | Lambda=1.00
  [BASE] !models--anthracite-core--Mistral-Small-3.2-24B-In
  !models--TheDrummer--Cydonia-24B-v4.3             : ███████████████████                                 39.5% (W:0.40 D:0.90 N:0.92 E:0.09)
  Cydonia-24B-v4x-Q8_0                              : ████████████████████                                40.2% (W:0.80 D:0.90 N:0.47 E:0.09)
  Cydonia-24B-v4y-Q8_0                              : ██████████                                          20.3% (W:0.40 D:0.90 N:0.47 E:0.09)

v12
[DELLA Audit] Layer: model.layers.0.mlp.up_proj.weight | Lambda=1.00
  [BASE] !models--anthracite-core--Mistral-Small-3.2-24B-In
  !models--TheDrummer--Cydonia-24B-v4.3             : ████████                                            17.5% (W:0.40 D:0.90 N:0.92 E:0.09)
  Cydonia-24B-v4q-Q8_0                              : ████████████████████████████████                    64.7% (W:0.40 D:0.90 N:3.41 E:0.09)
  Cydonia-24B-v4x-Q8_0                              : ████████                                            17.8% (W:0.80 D:0.90 N:0.27 E:0.09)

The following models were included in this merge:

• anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only
• BeaverAI/Cydonia-24B-v4x-GGUF
• BeaverAI/Cydonia-24B-v4y-GGUF
• TheDrummer/Cydonia-24B-v4.3

🙏 Thanks @mradermacher and other quantizers.

💾 GGUFs:
- mradermacher/Cyberdonia-24B-v8-GGUF
- mradermacher/Cyberdonia-24B-v8-i1-GGUF

⚙️ See this page for recommended settings.

🧙 Invocation Grimoires 🐙

🌋 Hellforged Parameters

mergekit_config.yml

architecture: MistralForCausalLM
base_model: B:\24B\!models--anthracite-core--Mistral-Small-3.2-24B-Instruct-2506-Text-Only
models:
  - model: B:\24B\Cydonia-24B-v4x-Q8_0
    parameters:
      weight: 0.8
      density: 0.9
      epsilon: 0.09
  - model: B:\24B\!models--TheDrummer--Cydonia-24B-v4.3
    parameters:
      weight: 0.4
      density: 0.9
      epsilon: 0.09
  - model: B:\24B\Cydonia-24B-v4y-Q8_0
    parameters:
      weight: 0.4
      density: 0.9
      epsilon: 0.09
merge_method: della
parameters:
  lambda: 1.0
  normalize: false
  int8_mask: false
  rescale: true
dtype: float32
out_dtype: bfloat16
tokenizer:
  source: union
chat_template: auto