Model Overview

LeoScorpius-7B is a 7 billion parameter language model developed by viethq188. This model was created through a slerp merge process, combining two distinct base models: viethq188/Rabbit-7B-v2-DPO-Chat and v1olet/v1olet_marcoroni-go-bruins-merge-7B. The merge operation, performed using mergekit, specifically integrated layers from AIDC-ai-business/Marcoroni-7B-v3 and Q-bert/MetaMath-Cybertron-Starling.

Key Characteristics

• Architecture: A merged model combining elements from DPO-tuned and Marcoroni-based models, suggesting a blend of instruction-following and potentially mathematical reasoning capabilities.
• Parameter Count: 7 billion parameters, offering a balance between performance and computational efficiency.
• Context Length: Supports an 8192-token context window, suitable for handling moderately long inputs and generating coherent responses.
• Merge Method: Utilizes a slerp (spherical linear interpolation) merge, which is often employed to combine the strengths of different models while maintaining performance.

Usage and Template

This model is designed to be used with an Alpaca-style instruction template for optimal performance. The recommended format is:

{system}
### Instruction:
{prompt}

### Response:

Potential Use Cases

Given its merged origins, LeoScorpius-7B is likely suitable for a range of general-purpose language tasks, including:

• Instruction following and chat applications.
• Text generation and summarization.
• Tasks benefiting from a model with combined DPO tuning and potentially enhanced reasoning components.