Model Overview

Kukedlc/neuronal-7b-Mlab is a 7 billion parameter language model developed by Kukedlc. It is a merged model, combining two distinct base models: mlabonne/NeuralDaredevil-7B and mlabonne/NeuralHermes-2.5-Mistral-7B. This merge was performed using the LazyMergekit tool, specifically employing the slerp (spherical linear interpolation) merge method.

Key Characteristics

• Architecture: Based on the Mistral-7B family, inheriting its efficient design.
• Parameter Count: 7 billion parameters, offering a balance between performance and computational requirements.
• Context Length: Supports a context window of 4096 tokens.
• Merge Method: Utilizes the slerp method with specific layer and parameter weighting, as detailed in the configuration, to blend the capabilities of its source models.

Intended Use Cases

This model is suitable for a variety of general-purpose text generation tasks, benefiting from the combined strengths of NeuralDaredevil-7B and NeuralHermes-2.5-Mistral-7B. Developers can integrate it into applications requiring conversational AI, content creation, or other language-based functionalities.