Gunulhona/Gemma-System-9B

merge

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

Merge Details

Merge Method

This model was merged using the Model Stock merge method using Gunulhona/Gemma-Ko-Merge as a base.

Models Merged

The following models were included in the merge:

• princeton-nlp/gemma-2-9b-it-SimPO
• Metin/Gemma-2-9b-it-TR-DPO-V1
• anthracite-org/magnum-v3-9b-customgemma2
• lemon07r/Gemma-2-Ataraxy-9B
• TheDrummer/Tiger-Gemma-9B-v3
• INSAIT-Institute/BgGPT-Gemma-2-9B-IT-v1.0

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: INSAIT-Institute/BgGPT-Gemma-2-9B-IT-v1.0
    layer_range: [0, 42]
  - model: lemon07r/Gemma-2-Ataraxy-9B
    layer_range: [0, 42]
  - model: Gunulhona/Gemma-Ko-Merge
    layer_range: [0, 42]
  - model: TheDrummer/Tiger-Gemma-9B-v3
    layer_range: [0, 42]
  - model: anthracite-org/magnum-v3-9b-customgemma2
    layer_range: [0, 42]
  - model: princeton-nlp/gemma-2-9b-it-SimPO
    layer_range: [0, 42]
  - model: Metin/Gemma-2-9b-it-TR-DPO-V1
    layer_range: [0, 42]
merge_method: model_stock
base_model: Gunulhona/Gemma-Ko-Merge
dtype: float16