license: gemma
base_model: google/gemma-4-12B-it
tags:
- abliterated
- uncensored
- gguf
- thai
language: - th
- en
pipeline_tag: text-generation
Gemma 4 12B Uncensored (Thai + English)
An abliterated (refusal-direction-removed) derivative of
google/gemma-4-12B-it.
This is a modified model derivative created under the Gemma Terms of Use.
What makes this different
Most abliterated models are measured using English-only refusal datasets,
which degrades the model's ability to write in other languages. This model was
abliterated using a Thai + English parallel prompt dataset, so it stays
fluent in Thai while removing over-refusals.
Files
| File | Size | Use case |
|---|---|---|
gemma-4-12B-it-uncensored-beta1-Q4_K_M.gguf |
~6.9 GB | General use (LM Studio, llama.cpp) |
gemma-4-12B-it-uncensored-beta1-F16.gguf |
~22.2 GB | Full precision / requantizing |
How it was made
- Base model: google/gemma-4-12B-it (dense)
- Method: abliteration (orthogonalizing the refusal direction out of the weights)
- Prompt dataset: Thai + English parallel prompts (harmful / harmless pairs).
Using Thai prompts in the measurement step keeps the model's Thai output natural. - Tool: jim-plus/llm-abliteration
Recommended sampling
Abliterated models can loop if the temperature is too low. Recommended settings:
--temp 0.6 --repeat-penalty 1.3 --repeat-last-n 512
Do not drop the temperature below ~0.6.
License & responsible use
Use is subject to the Gemma Terms of Use.
Removing refusals does not remove your responsibility — the prohibited-use
policy still applies. Do not use this model for illegal or harmful activity.