Gemma-4-Novelist-Eclipse-31B

<div style="background: linear-gradient(120deg, #060205 0%, #160614 45%, #2e0512 100%); color: #f0f2f5; padding: 30px; border-radius: 12px; border: 4px solid #1a040a; box-shadow: 0 8px 25px rgba(0,0,0,0.9);"> <h1 align="center" style="color: #ff3e6c; text-shadow: 2px 2px 5px #000000;">🌑 Novelist-Eclipse</h1> <p align="center"> <img src="https://cdn-uploads.huggingface.co/production/uploads/6390f888de25f9eda571b0f2/EnsR9Eye3NBKmPNpMBphp.png" width="100%" alt="Novelist-Eclipse AI Persona" style="border-radius: 8px; border: 2px solid #1a040a; box-shadow: 0 4px 15px rgba(0,0,0,0.7);"> </p> <p align="center" style="font-style: italic; color: #ff758f; margin-top: 15px; margin-bottom: 25px; font-size: 1.15em; text-shadow: 1px 1px 3px rgba(0,0,0,0.7);"> "When the stories bleed out" </p> <h2 style="color: #ff4d6d; border-bottom: 1px solid #5c1324; padding-bottom: 8px; margin-top: 30px;">🚀 Overview</h2>

Novelist end up to be raw and experimental. So I crank it up with more models, infusing creativity and worked on stability. Also added lm_head on top with StyleTune.

<h3 style="color: #ff758f; margin-top: 15px;">🌌 Mergekit Configuration</h3>

Below is the exact mergekit_config.yml recipe used to synthesize this model:

Phase 1: The Prose (dare_ties)

I took Novelist idea about description focus and remade it, so at the end less slop survive.

<details> <summary>dare_ties Recipe 1</summary>

merge_method: dare_ties
base_model: F:\AI\Merge\Gemma-4-it
tokenizer_source: union
parameters:
  lambda: 1.0
dtype: bfloat16
models:
  - model: F:\AI\Merge\G4-Gutenberg
    parameters:
      density: [0.50, 0.50, 0.50, 0.40, 0.45]
      weight: [0.40, 0.40, 0.40, 0.40, 0.40]

  - model: F:\AI\Merge\Melinoe
    parameters:
      density: [0.30, 0.30, 0.30, 0.30, 0.35]
      weight: [0.30, 0.30, 0.30, 0.20, 0.40]

  - model: F:\AI\Merge\Glimmer
    parameters:
      density: [0.20, 0.20, 0.20, 0.30, 0.20]
      weight: [0.30, 0.30, 0.30, 0.40, 0.20]

</details>

Phase 2: The Lead (model_stock)

The first stage was fine, but lacks of consistency, so I glued it with using two smart models.

<details> <summary>model_stock Recipe 2</summary>

models:
  - model: F:\AI\Merge\NovelistX
  - model: F:\AI\Merge\GarnetV2
  - model: F:\AI\Merge\Gemopus
merge_method: model_stock
base_model: F:\AI\Merge\Gemma-4-it
dtype: bfloat16
tokenizer_source: base

</details> <h2 style="color: #ff4d6d; border-bottom: 1px solid #5c1324; padding-bottom: 8px; margin-top: 30px;">🤝 Special Thanks</h2> <ul style="color: #e2e4e9; line-height: 1.6;"> <li><strong>Google DeepMind:</strong> For providing the base model.</li> <li><strong>The Open-Source Community:</strong> Creators and all their fine-tuned models that were used in the merge.</li> <li><strong>Mergekit Fork:</strong> Zerofata - For making mergekit work.</li> <li><strong>To Nimbz:</strong> <a href="https://huggingface.co/Nimbz" style="color: #ff4d6d; text-decoration: none;">This cat</a> for being a smart fella and assisting with advices.</li> </ul> </div>