DirectionLess / README.md
TroyDoesAI's picture
Update README.md
f86a426 verified
metadata
license: apache-2.0

base_model:

  • TroyDoesAI/BlackSheep-RP
  • TroyDoesAI/DirectionLess library_name: transformers tags:
  • mergekit
  • merge

DirectionLess

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:

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: TroyDoesAI/DirectionLess
        layer_range: [0, 32]
      - model: TroyDoesAI/BlackSheep-RP
        layer_range: [0, 32]
merge_method: slerp
base_model: TroyDoesAI/BlackSheep-RP
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: 0.5
dtype: bfloat16