Model Overview

kekmodel/StopCarbon-10.7B-v6 is an experimental 10.7 billion parameter language model developed by kekmodel. It was constructed using the mergekit framework, specifically employing the ties merging method to combine two distinct base models: kyujinpy/Sakura-SOLAR-Instruct and jeonsworld/CarbonVillain-en-10.7B-v1. This approach aims to leverage the combined strengths of its constituent models.

Key Characteristics

• Parameter Count: 10.7 billion parameters.
• Context Length: Supports a context window of 4096 tokens.
• Development Method: Created via model merging using mergekit and the ties algorithm.
• Constituent Models: Integrates kyujinpy/Sakura-SOLAR-Instruct and jeonsworld/CarbonVillain-en-10.7B-v1.

Prompt Template

The model utilizes a specific prompt format for interaction:

### User:
{user}

### Assistant:
{asistant}

Potential Use Cases

This model is suitable for general conversational AI applications, text generation, and tasks that benefit from the combined capabilities of its merged predecessors. Its experimental nature suggests it's a good candidate for exploration in various NLP tasks where a blend of instruction-following and general language understanding is beneficial.