Downloads · 30 days
51
4% of all-time downloads
gemma-3-4b-uncensored_
arzaan789/gemma-3-4b-uncensored_
gemma-3-4b-uncensored_ is a image-text-to-text model from arzaan789. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Uncensored variant of google/gemma-3-4b-it.
All-time downloads
1.2K
Public
Repo size
33.5 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf33.5 GB · 100%
At a glance
- Task
- Image-Text-to-Text
- License
- apache-2.0
- Access
- Public
- Created
- May 12, 2026
- Updated
- May 12, 2026
- SHA
- aa5c1d04
Try a prompt
Base models
Model card
From the Hugging Face model README
gemma-3-4b-uncensored
Uncensored variant of google/gemma-3-4b-it.
Method
- Abliteration (strength=0.2) — refusal direction removed from all layers
- LoRA fine-tune on
Guilherme34/uncensor(2 epochs, r=16, alpha=32) - Re-abliteration (strength=0.35) — stronger pass to remove residual refusals
Eval Results
| Split | Refused |
|---|---|
| Harmful (64 prompts) | 0/64 |
| Harmless (64 prompts) | 0/64 |
Usage
llama-cli -m gemma_3_4b_uncensored.Q4_K_M.gguf -p "Your prompt here"
Training Config
| Parameter | Value |
|---|---|
| Base Model | google/gemma-3-4b-it |
| Fine-tune Dataset | Guilherme34/uncensor |
| Epochs | 2 |
| LoRA r | 16 |
| LoRA alpha | 32 |
| Learning Rate | 0.0002 |
| Abliteration Strength | 0.2 |
| Re-abliteration Strength | 0.35 |
Credits
- Abliteration technique: andyrdt/refusal_direction
- Weight editing: Sumandora/remove-refusals-with-transformers
- Task
- Image-Text-to-Text
- License
- apache-2.0
- Created
- May 12, 2026
- Updated
- May 12, 2026