README.md

metadata

base_model:
  - MrRobotoAI/Thor-v1.1-8b-1024k
  - aifeifei798/llama3-8B-DarkIdol-2.2-Uncensored-1048K
  - MrRobotoAI/Thor-v1.1d-8b-1024k
  - MrRobotoAI/Thor-v1.1e-8b-1024k
library_name: transformers
tags:
  - mergekit
  - merge

merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the linear DARE merge method using aifeifei798/llama3-8B-DarkIdol-2.2-Uncensored-1048K as a base.

Models Merged

The following models were included in the merge:

• MrRobotoAI/Thor-v1.1-8b-1024k
• MrRobotoAI/Thor-v1.1d-8b-1024k
• MrRobotoAI/Thor-v1.1e-8b-1024k

Configuration

The following YAML configuration was used to produce this model:

 models:

  - model: MrRobotoAI/Thor-v1.1e-8b-1024k
    parameters:
      weight: 0.55
      density: 0.9
  - model: MrRobotoAI/Thor-v1.1-8b-1024k
    parameters:
      weight: 0.125
      density: 0.9
  - model: MrRobotoAI/Thor-v1.1d-8b-1024k
    parameters:
      weight: 0.2
      density: 0.9
  - model: aifeifei798/llama3-8B-DarkIdol-2.2-Uncensored-1048K
    parameters:
      weight: 0.125
      density: 0.9

 merge_method: dare_linear
 base_model: aifeifei798/llama3-8B-DarkIdol-2.2-Uncensored-1048K
 parameters:
  normalize: true
 dtype: float16