Rainbow_69_7B

technicolor consists of the following merge, which was then merged with the below LoRAs to produce rainbow:

slices:
  - sources:
      - model: paulml/OGNO-7B
        layer_range: [0, 32]
      - model: SanjiWatsuki/Kunoichi-DPO-v2-7B
        layer_range: [0, 32]
merge_method: slerp
base_model: SanjiWatsuki/Kunoichi-DPO-v2-7B
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

rainbow

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

Merge Details

Merge Method

This model was merged using the task arithmetic merge method using technicolor as a base.

Models Merged

The following models were included in the merge:

• technicolor + jeiku/Theory_of_Mind_Mistral
• technicolor + jeiku/Gnosis_Reformatted_Mistral
• technicolor + Undi95/Mistral-7B-small_pippa_limaRP-v3-lora
• technicolor + jeiku/Theory_of_Mind_Roleplay_Mistral

Configuration

The following YAML configuration was used to produce this model:

merge_method: task_arithmetic
base_model: technicolor
parameters:
  normalize: true
models:
  - model: technicolor+jeiku/Theory_of_Mind_Roleplay_Mistral
    parameters:
      weight: 1
  - model: technicolor+jeiku/Theory_of_Mind_Mistral
    parameters:
      weight: 1
  - model: technicolor+jeiku/Gnosis_Reformatted_Mistral
    parameters:
      weight: 1
  - model: technicolor+Undi95/Mistral-7B-small_pippa_limaRP-v3-lora
    parameters:
      weight: 1      
dtype: float16