Modelpublic

skarnam/SFT_fft_DARE_Resta

sourceHugging Faceupdated 1y agoView on Hugging Face

0likes7downloads

Model Card

merge

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:

—skarnam/SFT_fft_DARE
—skarnam/gemma-2-2b-safety_vector

Configuration

The following YAML configuration was used to produce this model:

yaml

models:
- model: skarnam/SFT_fft_DARE
  parameters:
    weight: 1.0
- model: skarnam/gemma-2-2b-safety_vector
  parameters:
    weight: 1.0
merge_method: linear
dtype: bfloat16
parameters:
  normalize: false
  int8_mask: true