Blazed-Forge/Gemma-4-Sphinsikus-Chronist-31B-GGUF

<style> .sphinsikus-container { background: linear-gradient(135deg, #2b1810 0%, #1a0f14 50%, #2a112c 100%); color: #e8d5c4; font-family: 'Segoe UI', Tahoma, Geneva, Verdana, sans-serif; padding: 40px 30px; border: 2px solid #b8860b; border-radius: 12px; box-shadow: 0 10px 30px rgba(0, 0, 0, 0.8), inset 0 0 40px rgba(184, 134, 11, 0.1); line-height: 1.6; }

.sphinsikus-container h1 { font-size: 2.0em !important; margin-top: 0; background: linear-gradient(90deg, #ffd700 0%, #ff8c00 50%, #d670ff 100%); -webkit-background-clip: text; -webkit-text-fill-color: transparent; text-shadow: 0px 0px 15px rgba(255, 215, 0, 0.2); text-align: center; letter-spacing: 2px; border-bottom: none !important; }

.sphinsikus-container img { display: block; margin: 20px auto 30px auto; max-width: 100%; border-radius: 8px; border: 4px solid #3d2314; box-shadow: 0 0 25px rgba(214, 112, 255, 0.4); }

.sphinsikus-container h2 { color: #ffb347 !important; border-bottom: 2px solid #8b5a2b !important; padding-bottom: 8px; margin-top: 40px; letter-spacing: 1px; font-size: 1.5em !important; }

.sphinsikus-container h3 { color: #d670ff !important; margin-top: 25px; }

.sphinsikus-container blockquote { font-style: italic; color: #f4e8d8; text-align: center; font-size: 1.1em; margin: 30px 0; border-left: 4px solid #ffd700 !important; border-right: 4px solid #d670ff !important; padding: 15px 20px; background: rgba(255, 215, 0, 0.05); border-radius: 8px; }

.sphinsikus-container pre { background: #140a08 !important; border: 1px solid #b8860b !important; border-radius: 6px; padding: 15px; box-shadow: inset 0 0 10px rgba(184, 134, 11, 0.1); }

.sphinsikus-container code { color: #ffb347; }

.sphinsikus-container table { width: 100%; border-collapse: collapse; margin-top: 20px; background: rgba(255, 255, 255, 0.03); border-radius: 8px; overflow: hidden; }

.sphinsikus-container th, .sphinsikus-container td { padding: 12px 15px; text-align: left; border-bottom: 1px solid #4a2f1d; }

.sphinsikus-container th { background: linear-gradient(90deg, #8b5a2b 0%, #4a2f1d 100%); color: #fff; font-weight: bold; }

.sphinsikus-container tr:hover { background: rgba(184, 134, 11, 0.1); }

.sphinsikus-container ul { list-style-type: none; padding-left: 0; }

.sphinsikus-container li { position: relative; padding-left: 25px; margin-bottom: 10px; }

.sphinsikus-container li::before { content: '⏳'; position: absolute; left: 0; top: 0; font-size: 0.9em; }

.sphinsikus-container hr { border: 0; border-top: 1px dashed #b8860b; margin: 50px 0 20px 0; } </style>

<div class="sphinsikus-container">

<div style="font-size: 0.9rem; color: #94a3b8; margin-bottom: 15px; text-align: center;">by Ateron</div>

⏳ 📜 Sphinsikus Chronist 📜 ⏳

This is a library of stories, ready to be told or written.

🐀 About the Model

This merge was made to keep grounded and realistic role-play. Gemma 4 often loses character adherence, slipping its tone into unnecessary lewdness. I tried to push this away while keeping it uncensored. The second focus was on writing stories and adventurous role-play.

• —Primary Focus: Character adherence. Role-play. Long context stories.

🗣️ Prompt Format

Please refer to the original `google/gemma-4-31b-it` for the correct chat template.

<|turn>user
Hello<turn|>
<|turn>model
Hi there<turn|>
<|turn>user
How are you?<turn|>
<|turn>model

🐀 Merge Details

I used mergekit to combine the specific advantages of models in three-step way:

Phase 1: The Adventure (dare_ties)

First, I took Our Gemsicle Model using it as a base. Then LatitudeGames/Equinox-31B and BirdToast/Gemma-4-31B-glimmer-rp-v0.1- I found them to be good in pro-active writing and role-play, so I carefully blend them together.

<details>

<summary>dare_ties Recipe 1</summary>

merge_method: dare_ties
base_model: F:\AI\Merge\Gemsicle
models:
  - model: F:\AI\Merge\Glimmer
    parameters:
      density: [0.30, 0.40, 0.60, 0.35, 0.40]
      weight: [0.30, 0.35, 0.50, 0.40, 0.30]
  - model: F:\AI\Merge\Equinox
    parameters:
      density: [0.70, 0.60, 0.50, 0.65, 0.60]
      weight: [0.45, 0.45, 0.40, 0.40, 0.50]
parameters:
  lambda: 1.0
  int8_mask: true
dtype: bfloat16

</details>

Phase 2: The Tone (dare_ties)

First, I took Our Gemsicle Model again using it as a base. Then Jackrong/Gemopus-4-31B-it and MRockatansky/Gemma-4-31B-storymaxxed2- This one supposed to give coherence in long rp, add more story-genres and keep it uncensored.

<details>

<summary>dare_ties Recipe 2</summary>

merge_method: dare_ties
base_model: F:\AI\Merge\Gemsicle
models:
  - model: F:\AI\Merge\Gemopus
    parameters:
      density: [0.60, 0.45, 0.30, 0.20, 0.20]
      weight: [0.50, 0.30, 0.10, 0.10, 0.10]
  - model: F:\AI\Merge\Gemma-4-31B-storymaxxed2
    parameters:
      density: [0.20, 0.20, 0.40, 0.40, 0.40]
      weight: [0.25, 0.25, 0.50, 0.40, 0.35]
parameters:
  lambda: 1.0
  int8_mask: true
dtype: bfloat16

</details>

Phase 3: Final Touch (della_linear)

There I keep rolling with Gemsicle as glued base and put two existing merges, picking the most important layers once more.

<details>

<summary>della_linear Recipe</summary>

merge_method: della_linear
base_model: F:\AI\Merge\Gemsicle
models:
  - model: F:\AI\Merge\SphinsikusPhase1
    parameters:
      density: [0.20, 0.20, 0.50, 0.50, 0.25]
      weight: [0.20, 0.35, 0.50, 0.65, 0.30]
  - model: F:\AI\Merge\SphinsikusPhase2
    parameters:
      density: [0.45, 0.45, 0.30, 0.40, 0.10]
      weight: [0.50, 0.30, 0.30, 0.35, 0.05]
parameters:
  epsilon: 0.08
  lambda: 1.0
  int8_mask: true
  normalize: true
dtype: bfloat16

</details>

🤝 Special Thanks

• —Google DeepMind: For providing the base model.
• —The Open-Source Community: Creators and all their fine-tunes models that was used in merge.
• —Mergekit Fork: Zerofata - Thank you for being so nice and making it possible.
• —To Nimbz: This fella for sharing brain cell.

</div>