README.md

metadata

base_model:
  - automerger/YamshadowExperiment28-7B
  - fearlessdots/WizardLM-2-7B-abliterated
library_name: transformers
tags:
  - mergekit
  - merge
  - mistral

YamWizard28-7B-abliterated

merge

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

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

• automerger/YamshadowExperiment28-7B
• fearlessdots/WizardLM-2-7B-abliterated

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: fearlessdots/WizardLM-2-7B-abliterated
        layer_range: [0, 32]
      - model: automerger/YamshadowExperiment28-7B
        layer_range: [0, 32]
merge_method: slerp
base_model: fearlessdots/WizardLM-2-7B-abliterated
parameters:
  t:
    - filter: self_attn
      value: [0.1, 0.6, 0.3, 0.8, 0.5]
    - filter: mlp
      value: [0.9, 0.4, 0.7, 0.2, 0.5]
    - value: 0.5
dtype: bfloat16