README.md

metadata

base_model:
  - Undi95/Utopia-13B
  - cognitivecomputations/WizardLM-1.0-Uncensored-Llama2-13b
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 della_linear merge method using Undi95/Utopia-13B as a base.

Models Merged

The following models were included in the merge:

• cognitivecomputations/WizardLM-1.0-Uncensored-Llama2-13b

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: cognitivecomputations/WizardLM-1.0-Uncensored-Llama2-13b
    parameters:
      weight: 0.5
      density: 0.8
  - model: cognitivecomputations/WizardLM-1.0-Uncensored-Llama2-13b
    parameters:
      weight: 0.5
      density: 0.8
merge_method: della_linear
base_model: Undi95/Utopia-13B
parameters:
  epsilon: 0.05
  lambda: 1
  int8_mask: true
dtype: bfloat16
tokenzer_source: union