mergekit-community/Phi-4-reasoning-Line-14b-karcher

merge

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

Merge Details

Merge Method

This model was merged using the Karcher Mean merge method using huihui-ai/phi-4-abliterated as a base.

Models Merged

The following models were included in the merge:

• AXCXEPT/phi-4-deepseek-R1K-RL-EZO
• microsoft/Phi-4-reasoning-plus
• microsoft/Phi-4-reasoning

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: microsoft/Phi-4-reasoning-plus
  - model: microsoft/Phi-4-reasoning
  - model: AXCXEPT/phi-4-deepseek-R1K-RL-EZO
  - model: huihui-ai/phi-4-abliterated
merge_method: karcher
base_model: huihui-ai/phi-4-abliterated
parameters:
  max_iter: 1000
normalize: true
int8_mask: true
tokenizer_source: base
dtype: bfloat16