README.md

metadata

base_model:
  - Qwen/Qwen2.5-Math-7B
  - katanemo/Arch-Function-7B
  - happzy2633/qwen2.5-7b-ins-v3
  - EVA-UNIT-01/EVA-Qwen2.5-7B-v0.1
  - Qwen/Qwen2.5-7B-Instruct
library_name: transformers
tags:
  - mergekit
  - merge

merge

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

Merge Details

Merge Method

This model was merged using the TIES merge method using happzy2633/qwen2.5-7b-ins-v3 as a base.

Models Merged

The following models were included in the merge:

• Qwen/Qwen2.5-Math-7B
• katanemo/Arch-Function-7B
• EVA-UNIT-01/EVA-Qwen2.5-7B-v0.1
• Qwen/Qwen2.5-7B-Instruct

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: happzy2633/qwen2.5-7b-ins-v3
    #no parameters necessary for base model
  - model: Qwen/Qwen2.5-Math-7B
    parameters:
      density: 0.4
      weight: 0.4
  - model: Qwen/Qwen2.5-7B-Instruct
    parameters:
      density: 0.2
      weight: 0.2
  - model: EVA-UNIT-01/EVA-Qwen2.5-7B-v0.1
    parameters:
      density: 0.3
      weight: 0.3
  - model: katanemo/Arch-Function-7B
    parameters:
      density: 0.1
      weight: 0.1
merge_method: ties
base_model: happzy2633/qwen2.5-7b-ins-v3
parameters:
  normalize: false
  int8_mask: true
dtype: bfloat16