metadata

base_model:
  - mistralai/Mistral-7B-v0.1
  - automerger/YamshadowExperiment28-7B
  - MaziyarPanahi/Calme-7B-Instruct-v0.9
  - EmbeddedLLM/Mistral-7B-Merge-14-v0.5
library_name: transformers
tags:
  - mergekit
  - merge

new_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 mistralai/Mistral-7B-v0.1 as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: MaziyarPanahi/Calme-7B-Instruct-v0.9
    parameters:
      weight: 0.3
      density: 0.5
  - model: automerger/YamshadowExperiment28-7B
    parameters:
      weight: 0.2
      density: 0.5
  - model: EmbeddedLLM/Mistral-7B-Merge-14-v0.5
    parameters:
      weight: 0.2
      density: 0.5
merge_method: dare_ties
base_model: mistralai/Mistral-7B-v0.1 
parameters:
  normalize: true
  int8_mask: true
dtype: float16