jeiku/Gattaca_3B

Mixed

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/RocketHermesZephyrBoros_3B as a base.

Models Merged

The following models were included in the merge:

• jeiku/RocketHermesZephyrBoros_3B + jeiku/Erotica_StableLM
• jeiku/RocketHermesZephyrBoros_3B + jeiku/No_Robots_Alpaca_StableLM
• jeiku/RocketHermesZephyrBoros_3B + jeiku/Toxic_DPO_StableLM
• jeiku/RocketHermesZephyrBoros_3B + jeiku/Everything_v3_128_StableLM
• jeiku/RocketHermesZephyrBoros_3B + jeiku/Bluemoon_cleaned_StableLM
• jeiku/RocketHermesZephyrBoros_3B + jeiku/Gnosis_StableLM
• jeiku/RocketHermesZephyrBoros_3B + jeiku/Theory_of_Mind_RP_128_StableLM

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: jeiku/RocketHermesZephyrBoros_3B+jeiku/Bluemoon_cleaned_StableLM
    parameters:
      weight: 0.30
      density: 0.25
  - model: jeiku/RocketHermesZephyrBoros_3B+jeiku/Toxic_DPO_StableLM
    parameters:
      weight: 0.25
      density: 0.25
  - model: jeiku/RocketHermesZephyrBoros_3B+jeiku/Theory_of_Mind_RP_128_StableLM
    parameters:
      weight: 0.35
      density: 0.25
  - model: jeiku/RocketHermesZephyrBoros_3B+jeiku/No_Robots_Alpaca_StableLM
    parameters:
      weight: 0.25
      density: 0.25
  - model: jeiku/RocketHermesZephyrBoros_3B+jeiku/Everything_v3_128_StableLM
    parameters:
      weight: 0.5
      density: 0.5
  - model: jeiku/RocketHermesZephyrBoros_3B+jeiku/Gnosis_StableLM
    parameters:
      weight: 0.4
      density: 0.4
  - model: jeiku/RocketHermesZephyrBoros_3B+jeiku/Erotica_StableLM
    parameters:
      weight: 0.20
      density: 0.20
merge_method: dare_ties
base_model: jeiku/RocketHermesZephyrBoros_3B
parameters:
dtype: bfloat16