TaxDocumentBeigePaint

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

⚠️ Development Notice – Stage 1 of 3
This is an early-stage merge prototype.
It has only undergone brief testing and exists to verify architecture and tokenizer stability.
Next steps:
2️⃣ Fine-tuning
3️⃣ DPO Swipe Studio alignment
then meeebeee Public release candidate

Use at your own risk — and please, for the love of anarchic cryptids, don’t production-deploy a beta. 🧌

Merge Details

Merge Method

This model was merged using the TIES merge method using aixonlab/Aether-12b as a base.

Models Merged

The following models were included in the merge:

• aixonlab/Aether-12b
• anthracite-org/magnum-v2-12b
• D1rtyB1rd/Egregore-Alice-RP-NSFW-12B
• nbeerbower/Mistral-Nemo-Gutenberg-Vitus-12B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: aixonlab/Aether-12b          
    parameters:
      weight: 0.40
  - model: anthracite-org/magnum-v2-12b   
    parameters:
      weight: 0.30
  - model: D1rtyB1rd/Egregore-Alice-RP-NSFW-12B
    parameters:
      weight: 0.15
  - model: nbeerbower/Mistral-Nemo-Gutenberg-Vitus-12B              
    parameters:
      weight: 0.15
merge_method: ties
base_model: aixonlab/Aether-12b
parameters:
  density: 0.45
dtype: float16

🧌 Maintained by: Your Mum
🧠 Variant: Text-only, 12B mistral nemo merge
💾 Upload date: October 2025
☕ Notes: Made with stubbornness, Python, and profanity.