Qwen2.5 7B YOYO Super

🚀 Achieve the Optimal Merged Model by Using One Basic Model and Two Fine-tuned Models!

This project aims to find the best way to merge one base model and two fine-tuned models, presenting the optimal results from numerous merging experiments.

🚀 Quick Start

The optimal merged models are available at the following links:

• Qwen2.5-7B-YOYO-super
• Qwen2.5-14B-YOYO-super

✨ Features

Previous Generation Formula

models:  
  - model: Qwen/Qwen2.5-7B-Instruct  
    parameters:  
      density: 1  
      weight: 1  
      lambda: 0.9
  - model: Qwen/Qwen2.5-7B-Instruct-1M  
    parameters:  
      density: 1  
      weight: 1  
      lambda: 0.9  
merge_method: della  
base_model: Qwen/Qwen2.5-7B  
parameters:  
  density: 1  
  weight: 1  
  lambda: 0.9  
  normalize: true  
  int8_mask: true  
dtype: bfloat16  
tokenizer_source: base

This formula was widely used in the merging process of the previous generation of models, but it has some deficiencies:

1. There is relatively little retention of knowledge of the basic model.
2. The mathematical and coding abilities have declined.

Current Generation Formula

models:
  - model: Qwen/Qwen2.5-7B-instruct
    parameters:
      density: 1 
      weight: 1
      lambda: 0.9
merge_method: della
base_model: Qwen/Qwen2.5-7B
parameters:
  density: 1
  weight: 1
  lambda: 0.9
  normalize: true
  int8_mask: true
dtype: float16
tokenizer_source: base
name: Qwen2.5-7B-della

models:
  - model: Qwen/Qwen2.5-7B-instruct-1M
    parameters:
      density: 1 
      weight: 1
      lambda: 0.9
merge_method: della
base_model: Qwen/Qwen2.5-7B
parameters:
  density: 1
  weight: 1
  lambda: 0.9
  normalize: true
  int8_mask: true
dtype: float16
tokenizer_source: base
name: Qwen2.5-7B-della-1M

models:
  - model: Qwen/Qwen2.5-7B-instruct
    parameters:
      density: 1 
      weight: 1
merge_method: ties
base_model: Qwen/Qwen2.5-7B
parameters:
  density: 1
  weight: 1
  normalize: true
  int8_mask: true
dtype: float16
tokenizer_source: base
name: Qwen2.5-7B-ties

models:
  - model: Qwen/Qwen2.5-7B-instruct-1M
    parameters:
      density: 1 
      weight: 1
merge_method: ties
base_model: Qwen/Qwen2.5-7B
parameters:
  density: 1
  weight: 1
  normalize: true
  int8_mask: true
dtype: float16
tokenizer_source: base
name: Qwen2.5-7B-ties-1M

merge_method: model_stock
base_model: Qwen/Qwen2.5-7B
models:
  - model: mergekit-community/Qwen2.5-7B-della
  - model: mergekit-community/Qwen2.5-7B-della-1M
  - model: mergekit-community/Qwen2.5-7B-ties
  - model: mergekit-community/Qwen2.5-7B-ties-1M
  - model: Qwen/Qwen2.5-7B-instruct-1M
  - model: Qwen/Qwen2.5-7B-instruct
tokenizer_source: base
int8_mask: true
normalize: true
dtype: float16

Except for a slight decrease in instruction following, significant improvements have been achieved in all other aspects. This formula will also be used in the development of the next generation of YOYO models.

📚 Documentation

YOYO-AI not only releases merged models with excellent performance but also publishes a complete and high-quality model merging formula, hoping to promote the progress of model merging technology in the open-source community with this!

Support

If you can use this formula when merging models, it will be the greatest support for YOYO-AI!

📄 License

The project is licensed under the apache-2.0 license.

📦 Model Information