Aryanne/Open-StarLake-Swap-7B

This is a merge of pre-trained language models created using mergekit, but my branch was used here

Merge Details

Merge Method

This model was merged using the task_swapping merge method using senseable/WestLake-7B-v2 as a base.

Models Merged

The following models were included in the merge:

• berkeley-nest/Starling-LM-7B-alpha

• NousResearch/Nous-Hermes-2-Mistral-7B-DPO

• openchat/openchat-3.5-0106

Prompt Format:

I prefer using this way, which seems to work.

Example using Koboldcpp:

Start Seq.:

\nYour_name: 

End Seq.:

\nCharacter_name: 

In Memory

### Instruction:
Character description.

Generate a endless verbose(very descriptive) role-play conversation with Character_name.

### Response:
Your_name: how are you doing babe? *Your_name approaches Character_name and kisses her in the lips*
Character_name: I'm fine, it's been an weird day. *Character_name blushes and hugs Your_name with love*

Configuration

The following YAML configuration was used to produce this model:

base_model:
  model:
    path: senseable/WestLake-7B-v2
dtype: bfloat16
merge_method: task_swapping
slices:
- sources:
  - layer_range: [0, 32]
    model:
      model:
        path: berkeley-nest/Starling-LM-7B-alpha
    parameters:
      diagonal_offset: 2.0
      weight: 0.72
  - layer_range: [0, 32]
    model:
      model:
        path: openchat/openchat-3.5-0106
    parameters:
      diagonal_offset: 4.0
      random_mask: 0.166
      random_mask_seed: 19519.0
      weight: 0.4
  - layer_range: [0, 32]
    model:
      model:
        path: NousResearch/Nous-Hermes-2-Mistral-7B-DPO
    parameters:
      diagonal_offset: 4.0
      random_mask: 0.125
      random_mask_seed: 990090.0
      weight: 0.666
  - layer_range: [0, 32]
    model:
      model:
        path: senseable/WestLake-7B-v2

Support

Please Consider donating: 0x190ac445974a989a87dd223f212a76ca0090c804