Novaciano/Pandemonium-3.2-1B
Novaciano/Pandemonium-3.2-1B is a 1 billion parameter language model, developed by Novaciano, built upon the Llama 3.2 architecture with a 32768 token context length. This model is a merge of several Llama 3.2-1B variants, specifically designed to minimize censorship and improve upon previous mixed models. It is optimized for uncensored text generation, making it suitable for applications requiring less restrictive content policies.
Loading preview...
Overview
Novaciano/Pandemonium-3.2-1B is a 1 billion parameter language model based on the Llama 3.2 architecture, featuring a 32768 token context length. Developed by Novaciano, this model is a "reboot" and improvement over previous mixing attempts, specifically focusing on reducing censorship.
Key Characteristics
- Uncensored Output: Explicitly designed and tested to be uncensored, aiming to provide less restricted text generation.
- Model Merging: Created using the Model Stock merging method, combining seven different Llama 3.2-1B variants, including
bunnycore/FuseChat-3.2-1B-Creative-RPas the base model. - Performance: Achieved 2nd best ranking on the UGI Scoreboard for Llama 3.2 1B models as of March 25, 2025.
Use Cases
This model is particularly suited for applications where:
- Minimizing Censorship is a primary requirement.
- Creative Writing and Roleplay might benefit from less restrictive content filters.
- Experimentation with Merged Models is desired, showcasing a specific approach to combining smaller models for targeted characteristics.