Gunulhona/Gemma-3-27B-v2

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:

• google/translategemma-27b-it
• Gunulhona/Gemma-3-27B

Configuration

The following YAML configuration was used to produce this model:

base_model: Gunulhona/Gemma-3-27B
dtype: bfloat16
merge_method: slerp
modules:
  multi_modal_projector:
    slices:
    - sources:
      - layer_range: [0, 0]
        model: Gunulhona/Gemma-3-27B
      - layer_range: [0, 0]
        model: google/translategemma-27b-it
  text_decoder:
    slices:
    - sources:
      - layer_range: [0, 62]
        model: Gunulhona/Gemma-3-27B
      - layer_range: [0, 62]
        model: google/translategemma-27b-it
  vision_tower:
    slices:
    - sources:
      - layer_range: [0, 27]
        model: Gunulhona/Gemma-3-27B
      - layer_range: [0, 27]
        model: google/translategemma-27b-it
parameters:
  t:
  - value: 0.45