gemma-3-12b-pt-InitializedEmbeds

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:

• google/gemma-3-12b-pt
• google/gemma-3-12b-it

Configuration

The following YAML configuration was used to produce this model:

merge_method: linear
dtype: bfloat16
models:
  - model: google/gemma-3-12b-pt
    parameters:
      weight: 1.0
  - model: google/gemma-3-12b-it
    parameters:
      weight: 0.0
tokenizer:
  source: google/gemma-3-12b-it
  tokens:
    <start_of_turn>:
      source: google/gemma-3-12b-it
      force: true
    <end_of_turn>:
      source: google/gemma-3-12b-it
      force: true