metadata

base_model:
  - Test157t/Heracleana-Maid-7b
  - Test157t/Heracleana-Maid-7b
  - jeiku/Futadom_Mistral
  - cognitivecomputations/samantha-1.1-westlake-7b
  - jeiku/Humiliation_Mistral
tags:
  - mergekit
  - merge

nitral

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: Test157t/Heracleana-Maid-7b+jeiku/Futadom_Mistral
        normalize: true
        layer_range: [0, 32]
      - model: cognitivecomputations/samantha-1.1-westlake-7b+jeiku/Humiliation_Mistral
        normalize: true
        layer_range: [0, 32]
merge_method: slerp
base_model: Test157t/Heracleana-Maid-7b
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