README.md

metadata

base_model:
  - NeuralNovel/Senzu-7B-v0.1-DPO
  - senseable/WestLake-7B-v2
library_name: transformers
tags:
  - mergekit
  - merge

merged

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

Merge Details

Merge Method

This model was merged using the task_swapping merge method using NeuralNovel/Senzu-7B-v0.1-DPO as a base.

Models Merged

The following models were included in the merge:

• senseable/WestLake-7B-v2

Configuration

The following YAML configuration was used to produce this model:

base_model:
  model:
    path: NeuralNovel/Senzu-7B-v0.1-DPO
dtype: bfloat16
merge_method: task_swapping
slices:
- sources:
  - layer_range: [0, 32]
    model:
      model:
        path: senseable/WestLake-7B-v2
    parameters:
      diagonal_offset: 2.0
      random_mask: 0.3333
      random_mask_seed: 98557.0
      weight: 0.75
  - layer_range: [0, 32]
    model:
      model:
        path: NeuralNovel/Senzu-7B-v0.1-DPO