kekmodel/StopCarbon-10.7B-v1

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

The kekmodel/StopCarbon-10.7B-v1 is an experimental 10.7 billion parameter language model with a 4096-token context length, created by kekmodel using a slerp merge of SOLAR-10.7B-Instruct-v1.0 and SauerkrautLM-SOLAR-Instruct. This model is designed for general instruction-following tasks, leveraging the combined strengths of its merged base models. It provides a robust foundation for applications requiring a capable and efficient language model.

Loading preview...

kekmodel/StopCarbon-10.7B-v1 Overview

StopCarbon-10.7B-v1 is an experimental 10.7 billion parameter language model developed by kekmodel. It was created using the mergekit tool, specifically employing the slerp (spherical linear interpolation) merge method. This model combines the capabilities of two distinct base models:

  • upstage/SOLAR-10.7B-Instruct-v1.0: A powerful instruction-tuned model.
  • VAGOsolutions/SauerkrautLM-SOLAR-Instruct: Another instruction-tuned variant based on the SOLAR architecture.

Key Characteristics

  • Architecture: Based on the SOLAR family, known for its efficient performance.
  • Parameter Count: 10.7 billion parameters, offering a balance between capability and computational efficiency.
  • Context Length: Supports a context window of 4096 tokens, suitable for processing moderately long inputs.
  • Development Method: Utilizes a slerp merge, which is a technique for combining the weights of multiple models to potentially achieve synergistic performance.

Prompt Template

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

### User:
{user}

### Assistant:
{asistant}

Good For

  • General Instruction Following: Excels at tasks requiring the model to adhere to specific instructions.
  • Experimental AI Development: Ideal for researchers and developers exploring merged model performance and capabilities.
  • Applications requiring a 10B-class model: Suitable for various NLP tasks where a model of this size offers a good trade-off between performance and resource usage.

Finetunes
1 models