TroyDoesAI/Unrestricted-Knowledge-Will-Not-Refuse-15B

Unbiased_Personality-15B

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

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

• TroyDoesAI/Little-Too-Toxic
• TroyDoesAI/UncensoredLM-Medium-NotLeft

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: TroyDoesAI/Little-Too-Toxic
        layer_range: [0, 49]
      - model: TroyDoesAI/UncensoredLM-Medium-NotLeft
        layer_range: [0, 49]
      
merge_method: slerp
base_model: TroyDoesAI/UncensoredLM-Medium-NotLeft
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.8 # fallback for rest of tensors
dtype: bfloat16