Modelpublic

mergekit-community/Qwen-ACTUALLY-Zeroed

sourceHugging Faceupdated 2y agoView on Hugging Face

0likes11downloads

Model Card

merge

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

This model was merged using the linear merge method.

The following models were included in the merge:

The following YAML configuration was used to produce this model:

yaml

models:
  - model: Qwen/Qwen2.5-0.5B-Instruct
    parameters:
      weight: 0.0
merge_method: linear
dtype: float16