Modelpublic

yamatazen/LinearWriter-12B

sourceHugging Faceupdated 1y agoView on Hugging Face

3likes17downloads

Model Card

image/png

LinearWriter-12B

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:

—shisa-ai/shisa-v2-mistral-nemo-12b
—nbeerbower/mistral-nemo-gutenberg-12B-v4
—natong19/Mistral-Nemo-Instruct-2407-abliterated
—Elizezen/Himeyuri-v0.1-12B

Configuration

The following YAML configuration was used to produce this model:

yaml

merge_method: linear
dtype: bfloat16
out_dtype: bfloat16
models:
  - model: natong19/Mistral-Nemo-Instruct-2407-abliterated # Uncensor
    parameters:
      weight: 1.0
  - model: nbeerbower/mistral-nemo-gutenberg-12B-v4 # Writing
    parameters:
      weight: [0.25, 0.3, 0.5, 0.6, 0.75]
  - model: Elizezen/Himeyuri-v0.1-12B # Japanese
    parameters:
      weight: [0.25, 0.3, 0.6, 0.3, 0.25]
  - model: shisa-ai/shisa-v2-mistral-nemo-12b # Japanese
    parameters:
      weight: [0.25, 0.3, 0.5, 0.3, 0.25]