metadata

base_model:
  - SicariusSicariiStuff/Impish_QWEN_14B-1M
  - deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
  - Qwen/Qwen2.5-14B-Instruct-1M
  - Zhihu-ai/Zhi-writing-dsr1-14b
  - huihui-ai/Qwen2.5-14B-Instruct-1M-abliterated
  - huihui-ai/Qwen2.5-14B-Instruct-abliterated-v2
  - Qwen/Qwen2.5-14B-Instruct
  - mergekit-community/Qwen2.5-14B-della-code
  - tanliboy/lambda-qwen2.5-14b-dpo-test
library_name: transformers
tags:
  - mergekit
  - merge
license: apache-2.0
language:
  - en
  - zh
pipeline_tag: text-generation

From the preliminary test results, the effect is really excellent!!!

This is definitely a very promising method for model merging!

The current optimal formula ratio is: instruction: reasoning: code = 6:2:1

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 Qwen/Qwen2.5-14B-Instruct as a base.

Models Merged

The following models were included in the merge:

instruction:(6)

reasoning:(2)

code:(1)

mergekit-community/Qwen2.5-14B-della-code

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: mergekit-community/Qwen2.5-14B-della-code
  - model: Zhihu-ai/Zhi-writing-dsr1-14b
  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
  - model: huihui-ai/Qwen2.5-14B-Instruct-1M-abliterated
  - model: huihui-ai/Qwen2.5-14B-Instruct-abliterated-v2
  - model: Qwen/Qwen2.5-14B-Instruct-1M
  - model: SicariusSicariiStuff/Impish_QWEN_14B-1M
  - model: tanliboy/lambda-qwen2.5-14b-dpo-test
  - model: Qwen/Qwen2.5-14B-Instruct
merge_method: karcher
base_model: Qwen/Qwen2.5-14B-Instruct
parameters:
  max_iter: 1000
normalize: true
int8_mask: true
tokenizer_source: base
dtype: float16