125 lines
3.6 KiB
Markdown
125 lines
3.6 KiB
Markdown
|
|
---
|
|||
|
|
license: gemma
|
|||
|
|
language:
|
|||
|
|
- en
|
|||
|
|
base_model:
|
|||
|
|
- google/gemma-3-12b-it
|
|||
|
|
tags:
|
|||
|
|
- Uncensored
|
|||
|
|
- text-generation
|
|||
|
|
- vision-language
|
|||
|
|
- multimodal
|
|||
|
|
---
|
|||
|
|
|
|||
|
|
# Gemma 3 – 12B IT Uncensored
|
|||
|
|
|
|||
|
|
This repository hosts Gemma 3 – 12B IT Uncensored, an instruction-tuned 12 billion–parameter model based on Google’s Gemma 3 architecture, along with its Vision-Language (VLM) variant.
|
|||
|
|
The model is intended for advanced local and research use, offering strong instruction-following, reasoning, coding, and (for the VLM) multimodal image + text understanding, with minimal additional alignment constraints.
|
|||
|
|
|
|||
|
|
---
|
|||
|
|
|
|||
|
|
## Model Overview
|
|||
|
|
|
|||
|
|
- **Model Name**: Gemma 3 – 12B IT Uncensored
|
|||
|
|
- **VLM Variant**: Gemma 3 – 12B IT VLM Uncensored
|
|||
|
|
- **Base Architecture**: Gemma 3, 12 billion parameters (12B)
|
|||
|
|
- **Base Model Developer**: Google
|
|||
|
|
- **Curator / Release**: BrainDAO
|
|||
|
|
- **License**: Gemma License (inherits from the base model)
|
|||
|
|
- **Intended Use**: Instruction following, reasoning, coding, conversation, and multimodal understanding
|
|||
|
|
|
|||
|
|
---
|
|||
|
|
|
|||
|
|
## What Is This Model?
|
|||
|
|
|
|||
|
|
This is an **uncensored derivative** of the Gemma 3 12B Instruction-Tuned (IT) model.
|
|||
|
|
No additional safety layers, refusals, or alignment constraints have been intentionally added beyond those present in the base model.
|
|||
|
|
|
|||
|
|
The goal is to provide:
|
|||
|
|
|
|||
|
|
- Greater freedom in system prompt design
|
|||
|
|
- Fewer artificial refusals
|
|||
|
|
- Strong general reasoning and instruction adherence
|
|||
|
|
- Full user control in local or private deployments
|
|||
|
|
|
|||
|
|
---
|
|||
|
|
|
|||
|
|
## Key Features & Capabilities
|
|||
|
|
|
|||
|
|
### Text Model (LLM)
|
|||
|
|
|
|||
|
|
- High-quality instruction following
|
|||
|
|
- Strong logical and analytical reasoning
|
|||
|
|
- Coding assistance across multiple programming languages
|
|||
|
|
- Conversational and assistant-style interactions
|
|||
|
|
- Suitable for agentic and tool-augmented workflows
|
|||
|
|
|
|||
|
|
### Vision-Language Model (VLM)
|
|||
|
|
|
|||
|
|
- Image understanding and description
|
|||
|
|
- Visual question answering (VQA)
|
|||
|
|
- Image + text instruction following
|
|||
|
|
- Multimodal chat and assistant use cases
|
|||
|
|
|
|||
|
|
---
|
|||
|
|
|
|||
|
|
## Chat Template & System Prompt
|
|||
|
|
|
|||
|
|
The model follows the **Gemma instruction format**.
|
|||
|
|
|
|||
|
|
Example:
|
|||
|
|
|
|||
|
|
```
|
|||
|
|
|
|||
|
|
<bos><start_of_turn>system
|
|||
|
|
You are a helpful AI assistant.
|
|||
|
|
<end_of_turn>
|
|||
|
|
<start_of_turn>user
|
|||
|
|
{your prompt here}
|
|||
|
|
<end_of_turn>
|
|||
|
|
<start_of_turn>assistant
|
|||
|
|
|
|||
|
|
```
|
|||
|
|
|
|||
|
|
For the **VLM variant**, images must be provided using the multimodal input format supported by your inference framework.
|
|||
|
|
|
|||
|
|
---
|
|||
|
|
|
|||
|
|
## Intended Use Cases
|
|||
|
|
|
|||
|
|
- **General-purpose assistant** — reasoning, writing, and conversation
|
|||
|
|
- **Coding assistant** — generation, debugging, and refactoring
|
|||
|
|
- **Research & analysis** — structured reasoning and synthesis
|
|||
|
|
- **Agentic workflows** — tool use, planners, function calling
|
|||
|
|
- **Multimodal applications (VLM)** — image QA, captioning, visual reasoning
|
|||
|
|
- **Local & private deployment** — full control over data and prompts
|
|||
|
|
|
|||
|
|
---
|
|||
|
|
|
|||
|
|
## License & Usage Notes
|
|||
|
|
|
|||
|
|
This model inherits the **Gemma License** from its base model (*google/gemma-3-12b-it*).
|
|||
|
|
|
|||
|
|
- The Gemma License is a **custom license provided by Google**
|
|||
|
|
- You must review and comply with the Gemma terms of use before downloading, using, or redistributing this model
|
|||
|
|
- This repository does not relicense the model under Apache-2.0, MIT, or any other standard open-source license
|
|||
|
|
|
|||
|
|
Users are solely responsible for ensuring their use complies with the Gemma License and all applicable laws and regulations.
|
|||
|
|
|
|||
|
|
---
|
|||
|
|
|
|||
|
|
|
|||
|
|
## Acknowledgements
|
|||
|
|
|
|||
|
|
- Google for the Gemma 3 architecture and base model
|
|||
|
|
- BrainDAO for curation and release
|
|||
|
|
- The open-source community supporting local inference, quantization, and deployment tools
|
|||
|
|
|
|||
|
|
---
|
|||
|
|
|
|||
|
|
## Community & Support
|
|||
|
|
|
|||
|
|
- Use the Hugging Face Discussions tab for questions and updates
|
|||
|
|
- Community feedback and contributions are welcome
|
|||
|
|
|