RichardErkhov/Cartinoe5930_-_DARE-Merging-8bits

Quantization made by Richard Erkhov.

Github

Discord

Request more models

DARE-Merging - bnb 8bits

• Model creator: https://huggingface.co/Cartinoe5930/
• Original model: https://huggingface.co/Cartinoe5930/DARE-Merging/

Original model description:

base_model: - openchat/openchat-3.5-0106 - mistralai/Mistral-7B-Instruct-v0.2 - Open-Orca/Mistral-7B-OpenOrca - WizardLM/WizardMath-7B-V1.1 tags: - mergekit - merge license: apache-2.0

result

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-Instruct-v0.2 as a base.

Models Merged

The following models were included in the merge:

• openchat/openchat-3.5-0106
• Open-Orca/Mistral-7B-OpenOrca
• WizardLM/WizardMath-7B-V1.1

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: mistralai/Mistral-7B-Instruct-v0.2
    # No parameters necessary for base model
  - model: Open-Orca/Mistral-7B-OpenOrca
    parameters:
      density: 0.5
      weight: 0.3
  - model: openchat/openchat-3.5-0106
    parameters:
      density: 0.5
      weight: 0.3
  - model: WizardLM/WizardMath-7B-V1.1
    parameters:
      density: 0.5
      weight: 0.3
merge_method: dare_ties
base_model: mistralai/Mistral-7B-Instruct-v0.2
parameters:
  normalize: true
dtype: float16