Fizzarolli/MN-12b-Sunrose
Fizzarolli/MN-12b-Sunrose is a 12 billion parameter language model created by Fizzarolli, merged using the passthrough method from MN-12b-Rosier-v1 and nemo-sunfall-v0.6.1-adapter-on-base. With a 32768 token context length, this model integrates capabilities from its constituent models. It is designed for general language generation tasks, leveraging the combined strengths of its merged components.
Loading preview...
Overview
Fizzarolli/MN-12b-Sunrose is a 12 billion parameter language model developed by Fizzarolli. This model was created using the passthrough merge method via mergekit, combining two distinct base models: Fizzarolli/MN-12b-Rosier-v1 and Fizzarolli/nemo-sunfall-v0.6.1-adapter-on-base. The merging process integrates the characteristics and capabilities of both source models into a single, cohesive unit.
Key Capabilities
- Merged Architecture: Benefits from the combined strengths of
MN-12b-Rosier-v1andnemo-sunfall-v0.6.1-adapter-on-base. - Parameter Count: Operates with 12 billion parameters, offering a balance between performance and computational efficiency.
- Extended Context Window: Supports a context length of 32768 tokens, enabling processing of longer inputs and generating more coherent, extended outputs.
Good For
- General Language Generation: Suitable for a wide array of text generation tasks due to its merged nature.
- Exploration of Merged Models: Ideal for developers interested in the outcomes and performance of models created through the
passthroughmerge method. - Applications Requiring Moderate Scale: Provides a robust solution for tasks that benefit from a 12B parameter model with a substantial context window.
Top 3 parameter combinations used by Featherless users for this model. Click a tab to see each config.