Model comparison
I wish there was a benchmark to test a model story writing capabilities automatically like there is a ayumi benchmark for roleplay
Self testing the model is always biased. I am using hestia model previously to generate my stories. At first i was happy since the model writing capabilities are really good
But i am not satisfied with the reasoning capability of hestia. I hope this model performs better!
Hestia vs Iambe-20b-DARE
The new model Iambe is not good for story writing. It follows instructions but generate rubbish and stupid scenarios. I don't know anything about model merging process but something went wrong and the noromaid unique writing style is not present in this model. The old model hestia is more creative and have a unique story writing style!
I think the trimming away that this new DARE process introduces removed a lot of Noromaid's little human details. You helped me to pinpoint the shift, thank you, I appreciate it.