---
language:
- ko
- en
license: mit
---

# Model Card for free-evo-qwen72b-v0.8

## Developed by : [Freewheelin](https://freewheelin-recruit.oopy.io/) AI Technical Team

## 1st place : 2024 4th May - avg. 81.28 [Open Llm Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)   
but this kicked away. maybe the explanation was not enough.

## Method
- We were inspired by this [Sakana project](https://sakana.ai/evolutionary-model-merge/)

## Process
- you need two models with the same architecture
- 1. choose one model and finetune the model to make a gap between the original one and fine-tuned one. it doesn't matter the evaluation score is higher or lower.
- 2. merge two of them
- 3. evaluate the merged model
- 4. finetune a specific evaluation part if you need to increase score of the part of the model. (sure it's not gonna work like you think. but try it)
- 5. merge again
- 6. evaluate again
- 7. keep going until evaluate avg is higher then original one

that's it. simple.   
you can make a framework to do this automatically.   

## Base Architecture 
- QWEN2

## Base Models
- several QWEN2 based models