metadata

language:
  - ko
  - en
license: mit

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

Developed by : Freewheelin AI Technical Team

but this kicked away. maybe the explanation was not enough.

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.
1. merge two of them
1. evaluate the merged model
1. 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)
1. merge again
1. evaluate again
1. keep going until evaluate avg is higher then original one

that's it. simple.