Sorihon/Chaotic-Harmony-24B
Sorihon/Chaotic-Harmony-24B is a 24 billion parameter language model created by Sorihon, merged using the DARE TIES method from TheDrummer/Cydonia-24B-v4.2.0 and Sorihon/Celestial-Order-24B-V3. This model leverages a 32768 token context length and is designed to combine the strengths of its base models through a specific merging configuration, making it suitable for general language generation tasks where a blend of capabilities is desired.
Loading preview...
Chaotic-Harmony-24B Overview
Sorihon/Chaotic-Harmony-24B is a 24 billion parameter language model resulting from a strategic merge of two pre-trained models: TheDrummer/Cydonia-24B-v4.2.0 and Sorihon/Celestial-Order-24B-V3. This model was constructed using the mergekit tool and specifically employed the DARE TIES merge method, which is known for combining model weights effectively.
Merge Details
The merging process utilized Sorihon/Celestial-Order-24B-V3 as the base model. The configuration involved specific density and weight parameters for each contributing model:
- TheDrummer/Cydonia-24B-v4.2.0: Applied with a density of 0.8 and a weight of 0.6.
- C:\Chaotic-Order-24B-V3: Applied with a density of 0.6 and a weight of 0.4.
This precise configuration aims to create a harmonious blend of the capabilities inherent in its constituent models, offering a unique performance profile. The model supports a substantial context length of 32768 tokens, allowing for processing and generating longer sequences of text.
Potential Use Cases
Given its merged nature and substantial parameter count, Chaotic-Harmony-24B is well-suited for applications requiring a robust understanding and generation of language, potentially excelling in areas where the strengths of its base models are complementary. Developers looking for a model that integrates diverse linguistic capabilities through a sophisticated merging technique may find this model particularly useful.