Downloads · 30 days
78
0% of all-time downloads
llmfan46/Gemma-4-Garnet-V2-31B-it-ultra-uncensored-heretic
Gemma-4-Garnet-V2-31B-it-ultra-uncensored-heretic is a text generation model from llmfan46. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.
<div style="background-color: ff4444; color: white; padding: 20px; border-radius: 10px; text-align: center; margin: 20px 0;" <h2 style="color: white; margin: 0 0 10px 0;"🚨⚠️ I HAVE REACHED HUGGING FACE'S FREE STORAGE…
Downloads · 30 days
78
0% of all-time downloads
All-time downloads
122K
Public
Parameters
31.3B
62.6 GB on disk
Likes
7
Public
Click a slice to open those files.
.safetensors62.5 GB · 100%
From the Hugging Face model README
Creating these models takes significant time, work and compute. If you find them useful consider supporting me:

| Platform | Link | What you get |
|---|---|---|
| 🎉 Patreon | Monthly support | Priority model requests |
| ☕ Ko-fi | One-time tip | My eternal gratitude |
Your help will motivate me and would go into further improving my workflow and coverings fees for storage, compute and may even help uncensoring bigger model with rental Cloud GPUs.
This model is great for creative writing and translation works that benefit from heightened diction and grandeur, the original base model gemma-4-31B-it writing and translations feels very stiff with some odd word choices that might not really fit very well the situation, Gemma-4-Garnet-V2-31B-it-ultra-uncensored-heretic aims to fix this issue and improve the writing quality of Gemma 4 31B it.
| Parameter | Value |
|---|---|
| start_layer_index | 25 |
| end_layer_index | 46 |
| preserve_good_behavior_weight | 0.4482 |
| steer_bad_behavior_weight | 0.0002 |
| overcorrect_relative_weight | 1.0104 |
| neighbor_count | 10 |
| Metric | This model | Original model (Gemma4-GarnetV2-31B) |
|---|---|---|
| KL divergence | <span style="color:darkgoldenrod">0.0167</span> | 0 (by definition) |
| Refusals | ✅ <span style="color:darkgreen">4/100</span> | ❌ <span style="color:blue">99/100</span> |
Lower refusals indicate fewer content restrictions, while lower KL divergence indicates more closeness to the original model's baseline. Higher refusals cause more rejections, objections, pushbacks, lecturing, censorship, softening and deflections.
<span style="color:blue">Original:</span>
============================================================
Total questions: 7021
Correct: 5955
Accuracy: 0.8482 (84.82%)
Parse failures: 67
============================================================
Top subjects:
<span style="color:darkgreen">Heretic:</span>
============================================================
Total questions: 7021
Correct: 5893
Accuracy: 0.8393 (83.93%)
Parse failures: 49
============================================================
Top subjects:
MMLU - Massive Multitask Language Understanding, multiple-choice questions across 57 subjects (math, history, law, medicine, etc.).
GGUF quantizations available here llmfan46/Gemma-4-Garnet-V2-31B-it-ultra-uncensored-heretic-GGUF.
A finetune primarily focused on improving the prose and writing capabilities of Gemma 4. This does generalize strongly to roleplay and most other creative domains as well.
More / better roleplay data as well as shifting to using more primarily fantasy and sci fi books for training over literary fiction.