README.md

metadata

base_model:
  - InferenceIllusionist/Excalibur-7b-DPO
  - yam-peleg/Experiment26-7B
  - MTSAIR/multi_verse_model
  - chihoonlee10/T3Q-Mistral-Orca-Math-DPO
library_name: transformers
tags:
  - mergekit
  - merge

hapsburg-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 InferenceIllusionist/Excalibur-7b-DPO as a base.

Models Merged

The following models were included in the merge:

• yam-peleg/Experiment26-7B
• MTSAIR/multi_verse_model
• chihoonlee10/T3Q-Mistral-Orca-Math-DPO

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: InferenceIllusionist/Excalibur-7b-DPO
  - model: MTSAIR/multi_verse_model
    parameters:
      density: 0.53
      weight: 0.4
  - model: yam-peleg/Experiment26-7B
    parameters:
      density: 0.53
      weight: 0.3
  - model: chihoonlee10/T3Q-Mistral-Orca-Math-DPO
    parameters:
      density: 0.53
      weight: 0.3
merge_method: dare_ties
base_model: InferenceIllusionist/Excalibur-7b-DPO
parameters:
  normalize: true
  int8_mask: true
dtype: bfloat16