README.md

metadata

base_model:
  - qingy2024/Qwen2.5-Math-14B-Instruct-Preview
  - arcee-ai/Virtuoso-Small
  - Qwen/Qwen2.5-14B
library_name: transformers
tags:
  - mergekit
  - merge
language:
  - zho
  - eng
  - fra
  - spa
  - por
  - deu
  - ita
  - rus
  - jpn
  - kor
  - vie
  - tha
  - ara

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:

• qingy2024/Qwen2.5-Math-14B-Instruct-Preview
• arcee-ai/Virtuoso-Small

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: qingy2024/Qwen2.5-Math-14B-Instruct-Preview
    parameters:
      weight: 0.35
      density: 0.6
  - model: arcee-ai/Virtuoso-Small
    parameters:
      weight: 0.65
      density: 0.8
base_model: Qwen/Qwen2.5-14B
merge_method: dare_ties
parameters:
  normalize: true
  int8_mask: true
dtype: bfloat16
tokenizer_source: Qwen/Qwen2.5-14B-Instruct