Skinwalker_3B

About This Model

This is the culmination of several weeks of work developing LoRAs for use with the StableLM 3B architecture. I have done away with all of the extraneous NSFW datasets to create a general purpose model more in line with modern model making sensibilities.

Note: This model will still output NSFW content if prompted to do so, but I have removed the humiliation and erotica training elements to bring the model more in line with the average users use case.

I hope you enjoy!

output

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/Rosa_v1_3B as a base.

Models Merged

The following models were included in the merge:

• jeiku/Rosa_v1_3B + jeiku/alpaca-cleaned_StableLM
• jeiku/Rosa_v1_3B + jeiku/Gnosis_StableLM
• jeiku/Rosa_v1_3B + jeiku/smol_PIPPA_StableLM
• jeiku/Rosa_v1_3B + jeiku/Toxic_DPO_StableLM
• jeiku/Rosa_v1_3B + jeiku/No_Robots_Alpaca_StableLM
• jeiku/Rosa_v1_3B + jeiku/Bluemoon_cleaned_StableLM

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: jeiku/Rosa_v1_3B+jeiku/Bluemoon_cleaned_StableLM
    parameters:
      weight: 0.15
      density: 0.166
  - model: jeiku/Rosa_v1_3B+jeiku/No_Robots_Alpaca_StableLM
    parameters:
      weight: 0.25
      density: 0.166
  - model: jeiku/Rosa_v1_3B+jeiku/Gnosis_StableLM
    parameters:
      weight: 0.2
      density: 0.166
  - model: jeiku/Rosa_v1_3B+jeiku/smol_PIPPA_StableLM
    parameters:
      weight: 0.15
      density: 0.166
  - model: jeiku/Rosa_v1_3B+jeiku/alpaca-cleaned_StableLM
    parameters:
      weight: 0.05
      density: 0.166
  - model: jeiku/Rosa_v1_3B+jeiku/Toxic_DPO_StableLM
    parameters:
      weight: 0.2
      density: 0.166
merge_method: dare_ties
base_model: jeiku/Rosa_v1_3B
parameters:
dtype: bfloat16