CorticalStack/crown-clown-7b-slerp

TEXT GENERATIONConcurrency Cost:1Model Size:7BQuant:FP8Ctx Length:4kPublished:Feb 19, 2024License:apache-2.0Architecture:Transformer Open Weights Cold

CorticalStack/crown-clown-7b-slerp is a 7 billion parameter language model created by CorticalStack, formed by a Spherical Linear Interpolation (SLERP) merge of mlabonne/AlphaMonarch-7B and bardsai/jaskier-7b-dpo-v5.6. This merged model leverages the strengths of its base components, offering a balanced performance profile for general language tasks within a 4096-token context window. It is particularly suited for applications requiring a blend of capabilities from its constituent models.

Loading preview...

Model Overview

CorticalStack/crown-clown-7b-slerp is a 7 billion parameter language model developed by CorticalStack. It is a product of a Spherical Linear Interpolation (SLERP) merge using mergekit, combining two distinct base models: mlabonne/AlphaMonarch-7B and bardsai/jaskier-7b-dpo-v5.6. This merging technique aims to create a model that inherits and balances the characteristics of its parent models.

Key Characteristics

  • Merge Method: Utilizes Spherical Linear Interpolation (SLERP) to blend the weights of the base models, specifically targeting different interpolation values for self-attention and MLP layers.
  • Base Models: Derived from mlabonne/AlphaMonarch-7B and bardsai/jaskier-7b-dpo-v5.6, suggesting a combination of their respective strengths.
  • Parameter Count: A 7 billion parameter model, offering a balance between performance and computational efficiency.
  • Context Length: Supports a context window of 4096 tokens.

Potential Use Cases

Given its merged nature, crown-clown-7b-slerp is likely suitable for a variety of general-purpose language generation and understanding tasks where a blend of capabilities from its constituent models is beneficial. Developers looking for a model with a unique combination of features from AlphaMonarch-7B and jaskier-7b-dpo-v5.6 may find this model particularly useful.