README.md

metadata

base_model:
  - beomi/Llama-3-KoEn-8B-Instruct-preview
  - asiansoul/Joah-Llama-3-MAAL-MLP-KoEn-8B-Reborn
  - NousResearch/Hermes-2-Pro-Llama-3-8B
  - saltlux/Ko-Llama3-Luxia-8B
  - defog/llama-3-sqlcoder-8b
  - Locutusque/llama-3-neural-chat-v2.2-8B
  - rombodawg/Llama-3-8B-Instruct-Coder
  - NousResearch/Meta-Llama-3-8B-Instruct
  - aaditya/Llama3-OpenBioLLM-8B
  - rombodawg/Llama-3-8B-Base-Coder-v3.5-10k
  - cognitivecomputations/dolphin-2.9.1-llama-3-8b
  - abacusai/Llama-3-Smaug-8B
  - NousResearch/Meta-Llama-3-8B
library_name: transformers
tags:
  - mergekit
  - merge

Joah-Remix-Llama-3-KoEn-8B-Reborn

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:

• beomi/Llama-3-KoEn-8B-Instruct-preview
• asiansoul/Joah-Llama-3-MAAL-MLP-KoEn-8B-Reborn
• NousResearch/Hermes-2-Pro-Llama-3-8B
• saltlux/Ko-Llama3-Luxia-8B
• defog/llama-3-sqlcoder-8b
• Locutusque/llama-3-neural-chat-v2.2-8B
• rombodawg/Llama-3-8B-Instruct-Coder
• NousResearch/Meta-Llama-3-8B-Instruct
• aaditya/Llama3-OpenBioLLM-8B
• rombodawg/Llama-3-8B-Base-Coder-v3.5-10k
• cognitivecomputations/dolphin-2.9.1-llama-3-8b
• abacusai/Llama-3-Smaug-8B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: NousResearch/Meta-Llama-3-8B
    # Base model providing a general foundation without specific parameters

  - model: NousResearch/Meta-Llama-3-8B-Instruct
    parameters:
      density: 0.65  
      weight: 0.25  
  
  - model: asiansoul/Joah-Llama-3-MAAL-MLP-KoEn-8B-Reborn
    parameters:
      density: 0.6  
      weight: 0.2 

  - model: beomi/Llama-3-KoEn-8B-Instruct-preview
    parameters:
      density: 0.55  
      weight: 0.125 
  
  - model: saltlux/Ko-Llama3-Luxia-8B
    parameters:
      density: 0.55  
      weight: 0.125  

  - model: cognitivecomputations/dolphin-2.9.1-llama-3-8b
    parameters:
      density: 0.55  
      weight: 0.05

  - model: aaditya/Llama3-OpenBioLLM-8B
    parameters:
      density: 0.55  
      weight: 0.05
      
  - model: rombodawg/Llama-3-8B-Instruct-Coder
    parameters:
      density: 0.55  
      weight: 0.05  

  - model: rombodawg/Llama-3-8B-Base-Coder-v3.5-10k
    parameters:
      density: 0.55  
      weight: 0.05      

  - model: defog/llama-3-sqlcoder-8b
    parameters:
      density: 0.55  
      weight: 0.05  

  - model: Locutusque/llama-3-neural-chat-v2.2-8B
    parameters:
      density: 0.55  
      weight: 0.05 

  - model: NousResearch/Hermes-2-Pro-Llama-3-8B
    parameters:
      density: 0.55  
      weight: 0.05 
  
  - model: abacusai/Llama-3-Smaug-8B
    parameters:
      density: 0.55  
      weight: 0.05 

merge_method: dare_ties
base_model: NousResearch/Meta-Llama-3-8B
parameters:
  int8_mask: true
dtype: bfloat16