jeiku/Sausage_3B

jeiku

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

Merge Details

Merge Method

This model was merged using the linear merge method.

Models Merged

The following models were included in the merge:

• jeiku/Rosa_v1_3B + jeiku/Humiliation_StableLM
• jeiku/Rosa_v1_3B + jeiku/Theory_of_Mind_128_StableLM
• jeiku/Rosa_v1_3B + jeiku/Bluemoon_cleaned_StableLM
• jeiku/Rosa_v1_3B + jeiku/Erotica_StableLM
• jeiku/Rosa_v1_3B + jeiku/Everything_v3_128_StableLM
• jeiku/Rosa_v1_3B + jeiku/Toxic_DPO_StableLM
• jeiku/Rosa_v1_3B + jeiku/No_Robots_Alpaca_StableLM
• jeiku/Rosa_v1_3B + jeiku/Gnosis_StableLM
• jeiku/Rosa_v1_3B + jeiku/Theory_of_Mind_RP_128_StableLM

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: jeiku/Rosa_v1_3B+jeiku/Theory_of_Mind_128_StableLM
    parameters:
      weight: 0.3
  - model: jeiku/Rosa_v1_3B+jeiku/Everything_v3_128_StableLM
    parameters:
      weight: 0.45
  - model: jeiku/Rosa_v1_3B+jeiku/Gnosis_StableLM
    parameters:
      weight: 1
  - model: jeiku/Rosa_v1_3B+jeiku/Toxic_DPO_StableLM
    parameters:
      weight: 0.5
  - model: jeiku/Rosa_v1_3B+jeiku/No_Robots_Alpaca_StableLM
    parameters:
      weight: 0.5
  - model: jeiku/Rosa_v1_3B+jeiku/Theory_of_Mind_RP_128_StableLM
    parameters:
      weight: 0.35
  - model: jeiku/Rosa_v1_3B+jeiku/Humiliation_StableLM
    parameters:
      weight: 0.25
  - model: jeiku/Rosa_v1_3B+jeiku/Bluemoon_cleaned_StableLM
    parameters:
      weight: 0.4
  - model: jeiku/Rosa_v1_3B+jeiku/Erotica_StableLM
    parameters:
      weight: 0.5
merge_method: linear
dtype: float16