Modelpublic

Parum-Lucis/gemma-3-270m-cpt-wordpiece-2K-5y-merged-linear

sourceHugging Faceupdated 2mo agoView on Hugging Face

0likes13downloads

Model Card

gemma-3-270m-cpt-wordpiece-2K-5y-merged-linear

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

Merge Details

Merge Method

This model was merged using the Linear merge method.

Models Merged

The following models were included in the merge:

—rafurafu/gemma-3-270m-cpt-wordpiece-2K-5y
—google/gemma-3-270m

Configuration

The following YAML configuration was used to produce this model:

yaml

dtype: bfloat16
merge_method: linear
modules:
  default:
    slices:
    - sources:
      - layer_range: [0, 18]
        model: rafurafu/gemma-3-270m-cpt-wordpiece-2K-5y
        parameters:
          weight: 0.5
      - layer_range: [0, 18]
        model: google/gemma-3-270m
        parameters:
          weight: 0.5
tokenizer:
  source: base