README.md

metadata

base_model:
  - mergekit-community/mergekit-slerp-lupllmg
  - mergekit-community/mergekit-slerp-rayqjvs
  - mergekit-community/mergekit-della_linear-byjvyzy
library_name: transformers
tags:
  - mergekit
  - merge

merge

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

Merge Details

Merge Method

This model was merged using the Linear DELLA merge method using mergekit-community/mergekit-slerp-lupllmg as a base.

Models Merged

The following models were included in the merge:

• mergekit-community/mergekit-slerp-rayqjvs
• mergekit-community/mergekit-della_linear-byjvyzy

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: mergekit-community/mergekit-slerp-lupllmg
    parameters:
      weight: 0.4
      density: 0.8
  - model: mergekit-community/mergekit-slerp-rayqjvs
    parameters:
      weight: 0.4
      density: 0.8
  - model: mergekit-community/mergekit-della_linear-byjvyzy
    parameters:
      weight: 0.2
      density: 0.2
merge_method: della_linear
base_model: mergekit-community/mergekit-slerp-lupllmg
parameters:
  epsilon: 0.05
  lambda: 1
dtype: bfloat16
tokenizer_source: base