kunoichi-squared-model_stock-7B

This is a merge of pre-trained language models created using mergekit. The base model used is literally the base model. While the result is syntactically stable, there was something about the resulting narrative generation that seemed off. Perhaps more than 2 models are required for successful model stock merges. Tested primarily with temperature 1-1.1 and minP 1.01-1.03 using ChatML prompts.

Merge Details

Merge Method

This model was merged using the Model Stock merge method using mistralai/Mistral-7B-v0.1 as a base.

Models Merged

The following models were included in the merge:

• SanjiWatsuki/Kunoichi-DPO-v2-7B
• SanjiWatsuki/Kunoichi-7B

Configuration

The following YAML configuration was used to produce this model:

base_model: mistralai/Mistral-7B-v0.1
dtype: float16
merge_method: model_stock
slices:
- sources:
  - layer_range: [0, 32]
    model: mistralai/Mistral-7B-v0.1
  - layer_range: [0, 32]
    model: SanjiWatsuki/Kunoichi-7B
  - layer_range: [0, 32]
    model: SanjiWatsuki/Kunoichi-DPO-v2-7B