rnosov/gemma-3-27b-leopard

merged_model

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:

• /dev/shm/model_staging/TheDrummer_Big-Tiger-Gemma-27B-v3
• /dev/shm/model_staging/unsloth_gemma-3-27b-pt

Configuration

The following YAML configuration was used to produce this model:

base_model: /dev/shm/model_staging/unsloth_gemma-3-27b-pt
dtype: bfloat16
merge_method: slerp
models:
- model: /dev/shm/model_staging/unsloth_gemma-3-27b-pt
  parameters:
    t: 0.0
- model: /dev/shm/model_staging/TheDrummer_Big-Tiger-Gemma-27B-v3
  parameters:
    t: 1.0
parameters:
  t: 0.5
tokenizer_source: /dev/shm/model_staging/TheDrummer_Big-Tiger-Gemma-27B-v3