CoolFace
Modelpublic

billxbf/wsdm-qwen14b_dare_dslerp

sourceHugging Faceupdated 2y agoView on Hugging Face
0likes3downloads
Model Card

qwen14bdaredslerp

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:

  • —/group-volume/binfeng/wsdm/ckpt/qwen14bddare
  • —/group-volume/binfeng/wsdm/ckpt/qwen14b_dare

Configuration

The following YAML configuration was used to produce this model:

yaml
base_model: /group-volume/binfeng/wsdm/ckpt/qwen14b_dare
dtype: float16
merge_method: slerp
parameters:
  t:
  - value: 0.3
slices:
- sources:
  - layer_range: [0, 48]
    model: /group-volume/binfeng/wsdm/ckpt/qwen14b_dare
  - layer_range: [0, 48]
    model: /group-volume/binfeng/wsdm/ckpt/qwen14b_d_dare