kekmodel/StopCarbon-10.7B-v4

TEXT GENERATIONConcurrency Cost:1Model Size:10.7BQuant:FP8Ctx Length:4kLicense:cc-by-nc-sa-4.0Architecture:Transformer Open Weights Cold

kekmodel/StopCarbon-10.7B-v4 is a 10.7 billion parameter experimental language model created by kekmodel using the mergekit framework. This model is a merge of several existing models, including kyujinpy/Sakura-SOLAR-Instruct, jeonsworld/CarbonVillain-en-10.7B-v1, kekmodel/StopCarbon-10.7B-v1, and kekmodel/StopCarbon-10.7B-v2, utilizing the 'ties' merge method. It is designed for general language generation tasks, leveraging the combined strengths of its constituent models.

Loading preview...

kekmodel/StopCarbon-10.7B-v4 Overview

kekmodel/StopCarbon-10.7B-v4 is an experimental 10.7 billion parameter language model developed by kekmodel. It was constructed using the mergekit framework, specifically employing the ties merge method to combine the capabilities of several distinct models. This approach aims to synthesize the strengths of its base models into a single, more versatile entity.

Key Characteristics

  • Parameter Count: 10.7 billion parameters, offering a balance between performance and computational requirements.
  • Merge Method: Utilizes the ties merge method via mergekit, indicating a specific strategy for combining model weights.
  • Constituent Models: Formed from a merge of:
    • kyujinpy/Sakura-SOLAR-Instruct
    • jeonsworld/CarbonVillain-en-10.7B-v1
    • kekmodel/StopCarbon-10.7B-v1
    • kekmodel/StopCarbon-10.7B-v2

Prompt Template

The model is designed to be used with a specific prompt template for instruction-following tasks:

### User:
{user}

### Assistant:
{asistant}

Potential Use Cases

Given its experimental nature and the merging of multiple instruction-tuned models, StopCarbon-10.7B-v4 is suitable for:

  • General Text Generation: Creating coherent and contextually relevant text.
  • Instruction Following: Responding to user prompts and instructions in a structured manner.
  • Research and Experimentation: Exploring the effects of model merging techniques on performance and capabilities.

Finetunes
1 models