Modelpublic

mergekit-community/mergekit-dare_ties-ymiqjtz

sourceHugging Faceupdated 2y agoView on Hugging Face

0likes24downloads

Model Card

merge

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

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using amazingvince/Not-WizardLM-2-7B as a base.

Models Merged

The following models were included in the merge:

—MaziyarPanahi/Calme-7B-Instruct-v0.9
—Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerp
—cognitivecomputations/dolphin-2.8-mistral-7b-v02

Configuration

The following YAML configuration was used to produce this model:

yaml

models:
  - model: MaziyarPanahi/Calme-7B-Instruct-v0.9
    parameters:
      density: 0.53
      weight: 0.33333333
  - model: cognitivecomputations/dolphin-2.8-mistral-7b-v02
    parameters:
      density: 0.53
      weight: 0.33333333
  - model: Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerp
    parameters:
      density: 0.53
      weight: 0.33333333

merge_method: dare_ties
base_model: amazingvince/Not-WizardLM-2-7B
parameters:
  normalize: false
  int8_mask: true
dtype: float16