metadata

base_model:
  - saltlux/Ko-Llama3-Luxia-8B
  - beomi/Llama-3-KoEn-8B-preview
  - NousResearch/Meta-Llama-3-8B
  - dreamgen-preview/opus-v1.2-llama-3-8b-instruct-run3.5-epoch2.5
  - openlynn/Llama-3-Soliloquy-8B-v2
  - lodrick-the-lafted/Olethros-8B
  - dreamgen-preview/opus-v1.2-llama-3-8b-base-run3.4-epoch2
  - NousResearch/Meta-Llama-3-8B-Instruct
  - beomi/Llama-3-KoEn-8B-Instruct-preview
library_name: transformers
tags:
  - mergekit
  - merge

YachtRP-Llama-3-KoEn-8B

🚨 Yacht Korean / English RP Merge Test Model. Please note that this version is an English/Korean RP test version, so it may not operate properly. The answers may contain inappropriate content, so please use them carefully for testing purposes only.

model_stock method is not good performance by my human rp test. so use dare_tie for both kr / en

All licenses belong to those below, so please use it for personal and academic use only.🚨

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using NousResearch/Meta-Llama-3-8B as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: NousResearch/Meta-Llama-3-8B
  - model: NousResearch/Meta-Llama-3-8B-Instruct
    parameters:
      density: 0.60  
      weight: 0.25  
  - model: beomi/Llama-3-KoEn-8B-preview
    parameters:
      density: 0.55  
      weight: 0.2
  - model: saltlux/Ko-Llama3-Luxia-8B
    parameters:
      density: 0.55  
      weight: 0.1
  - model: beomi/Llama-3-KoEn-8B-Instruct-preview
    parameters:
      density: 0.55  
      weight: 0.15 
  - model: dreamgen-preview/opus-v1.2-llama-3-8b-base-run3.4-epoch2
    parameters:
      density: 0.55  
      weight: 0.1  
  - model: dreamgen-preview/opus-v1.2-llama-3-8b-instruct-run3.5-epoch2.5
    parameters:
      density: 0.55  
      weight: 0.1  
  - model: openlynn/Llama-3-Soliloquy-8B-v2
    parameters:
      density: 0.55  
      weight: 0.1
  - model: lodrick-the-lafted/Olethros-8B
    parameters:
      density: 0.55  
      weight: 0.1  
merge_method: dare_ties
base_model: NousResearch/Meta-Llama-3-8B
parameters:
  int8_mask: true
dtype: bfloat16

Test

Citation instructions

Ko-Llama3-Luxia-8B

@article{kollama3luxiamodelcard,
  title={Ko Llama 3 Luxia Model Card},
  author={AILabs@Saltux},
  year={2024},
  url={https://huggingface.co/saltlux/Ko-Llama3-Luxia-8B/blob/main/README.md}
}

Original Llama-3

@article{llama3modelcard,
title={Llama 3 Model Card},
author={AI@Meta},
year={2024},
url={https://github.com/meta-llama/llama3/blob/main/MODEL_CARD.md}
}

Llama-3-Open-Ko

@article{llama3koen,
  title={Llama-3-KoEn},
  author={L, Junbum},
  year={2024},
  url={https://huggingface.co/beomi/Llama-3-KoEn-8B}
}