You can deploy this model and start earning money today!

mergekit-community/
mergekit-dare_ties-psxhlrx

Name: mergekit-dare_ties-psxhlrx
Availability: InStock

Views

No views yet

merge

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

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using Qwen/Qwen2.5-14B as a base.

Models Merged

The following models were included in the merge:

Krystalan/DRT-14B
netease-youdao/Confucius-o1-14B
huihui-ai/Qwen2.5-Coder-14B-Instruct-abliterated

Configuration

The following YAML configuration was used to produce this model:

yaml

models:
  - model: Qwen/Qwen2.5-14B
    #no parameters necessary for base model
  - model: huihui-ai/Qwen2.5-Coder-14B-Instruct-abliterated
    parameters:
      density: 0.53
      weight: 0.4
  - model: Krystalan/DRT-14B
    parameters:
      density: 0.5
      weight: 0.3
  - model: netease-youdao/Confucius-o1-14B
    parameters:
      density: 0.5
      weight: 0.3

merge_method: dare_ties
base_model: Qwen/Qwen2.5-14B
parameters:
  normalize: true
  int8_mask: true
dtype: float16

mergekit-community/mergekit-dare_ties-psxhlrx