README.md

metadata

base_model:
  - davidkim205/ko-gemma-2-9b-it
  - valeriojob/MedGPT-Gemma2-9B-BA-v.1
  - Shaleen123/gemma2-9b-medical
  - anthracite-org/magnum-v3-9b-customgemma2
  - ChuGyouk/ko-med-gemma-2-9b-it-merge2
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 breadcrumbs_ties merge method using anthracite-org/magnum-v3-9b-customgemma2 as a base.

Models Merged

The following models were included in the merge:

• davidkim205/ko-gemma-2-9b-it
• valeriojob/MedGPT-Gemma2-9B-BA-v.1
• Shaleen123/gemma2-9b-medical
• ChuGyouk/ko-med-gemma-2-9b-it-merge2

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: davidkim205/ko-gemma-2-9b-it
    layer_range: [0, 42]
    parameters:
        weight: 1
        density: 0.7
        gamma: 0.03
  - model: ChuGyouk/ko-med-gemma-2-9b-it-merge2
    layer_range: [0, 42]
    parameters:
        weight: 1
        density: 0.42
        gamma: 0.03
  - model: Shaleen123/gemma2-9b-medical
    layer_range: [0, 42]
    parameters:
        weight: 1
        density: 0.42
        gamma: 0.03
  - model: valeriojob/MedGPT-Gemma2-9B-BA-v.1
    layer_range: [0, 42]
    parameters:
        weight: 1
        density: 0.42
        gamma: 0.03

merge_method: breadcrumbs_ties
base_model: anthracite-org/magnum-v3-9b-customgemma2 #rtzr/ko-gemma-2-9b-it+ghost613/gemma9_on_korean_summary_events # lora model loading
dtype: float16