nkpz/Gemma-Bloom-2-9B-it-Uncensored-DeLMAT
nkpz/Gemma-Bloom-2-9B-it-Uncensored-DeLMAT is a 9 billion parameter instruction-tuned language model based on the Gemma-Bloom-2 architecture, featuring a 16384-token context length. This model has been specifically decensored using a custom training script guided by activation analysis, differentiating it from standard instruction-tuned models. Its primary characteristic is its uncensored nature, making it suitable for applications requiring less restrictive content generation. The model is designed for developers seeking a powerful, open-source alternative with enhanced freedom in output.
Loading preview...
Model Overview
nkpz/Gemma-Bloom-2-9B-it-Uncensored-DeLMAT is an instruction-tuned language model built upon the Gemma-Bloom-2 architecture, featuring 9 billion parameters and a substantial 16384-token context window. Its most notable characteristic is its "decensored" nature, achieved through a unique training methodology. This process involved a custom training script that utilized activation guidance, similar to ablation techniques, to modify the model's behavior regarding content restrictions.
Key Capabilities
- Decensored Output: The model is specifically engineered to produce less restricted content compared to conventionally trained instruction-tuned models.
- Instruction Following: As an instruction-tuned model, it is designed to respond to user prompts and instructions effectively.
- Large Context Window: A 16384-token context length allows for processing and generating longer, more complex texts.
Good For
- Unrestricted Content Generation: Ideal for use cases where standard models might be overly restrictive or refuse to generate certain types of content.
- Exploratory AI Development: Suitable for researchers and developers experimenting with model safety, bias, and control mechanisms.
- Creative Applications: Can be leveraged in creative writing, role-playing, or other applications where a broader range of expression is desired.
The custom training script used for decensoring is open-sourced under the MIT license and available on GitHub, providing transparency into its development.