jeiku/Luna_3B

lower

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

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using jeiku/ToxicNoRobotsRosaHermesBoros_3B as a base.

Models Merged

The following models were included in the merge:

• jeiku/ToxicNoRobotsRosaHermesBoros_3B + jeiku/Theory_of_Mind_StableLM
• jeiku/ToxicNoRobotsRosaHermesBoros_3B + jeiku/Everything_v3_StableLM
• jeiku/ToxicNoRobotsRosaHermesBoros_3B + jeiku/Bluemoon_cleaned_StableLM
• jeiku/ToxicNoRobotsRosaHermesBoros_3B + jeiku/Capybara_StableLM
• jeiku/ToxicNoRobotsRosaHermesBoros_3B + jeiku/alpaca-cleaned_StableLM

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: jeiku/ToxicNoRobotsRosaHermesBoros_3B+jeiku/alpaca-cleaned_StableLM
    parameters:
      weight: 0.1
      density: 1
  - model: jeiku/ToxicNoRobotsRosaHermesBoros_3B+jeiku/Capybara_StableLM
    parameters:
      weight: 0.1
      density: 1
  - model: jeiku/ToxicNoRobotsRosaHermesBoros_3B+jeiku/Everything_v3_StableLM
    parameters:
      weight: 0.1
      density: 1
  - model: jeiku/ToxicNoRobotsRosaHermesBoros_3B+jeiku/Theory_of_Mind_StableLM
    parameters:
      weight: 0.15
      density: 1
  - model: jeiku/ToxicNoRobotsRosaHermesBoros_3B+jeiku/Bluemoon_cleaned_StableLM
    parameters:
      weight: 0.1
      density: 1
merge_method: dare_ties
base_model: jeiku/ToxicNoRobotsRosaHermesBoros_3B
parameters:
dtype: bfloat16