Edit model card

MixSwap

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 Aryanne/Open-StarLake-Swap-7B as a base.

Models Merged

The following models were included in the merge:

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: Aryanne/Open-StarLake-Swap-7B
dtype: bfloat16
merge_method: task_swapping
slices:
- sources:
  - layer_range: [0, 32]
    model:
      model:
        path: l3utterfly/mistral-7b-v0.1-layla-v4-chatml
    parameters:
      diagonal_offset: 4.0
      random_mask: 0.1
      random_mask_seed: 1956557.0
      weight: 0.4
  - layer_range: [0, 32]
    model:
      model:
        path: cognitivecomputations/dolphin-2.2.1-mistral-7b
    parameters:
      diagonal_offset: 4.0
      random_mask: 0.1
      random_mask_seed: 18019.0
      weight: 0.333
  - layer_range: [0, 32]
    model:
      model:
        path: teknium/Mistral-Trismegistus-7B
    parameters:
      diagonal_offset: 4.0
      random_mask: 0.05
      random_mask_seed: 666666.0
      weight: 0.5
  - layer_range: [0, 32]
    model:
      model:
        path: Aryanne/Open-StarLake-Swap-7B
Downloads last month
576
Safetensors
Model size
7.24B params
Tensor type
BF16
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for Aryanne/MixSwap