this is so freaking cool , a local setup to recursively refine and critique such generative creations would be ideal . the back and forth of loading this up into the system if made any manual changes seems to be the largest bottleneck . awesome works !
![[1hr Talk] Intro to Large Language Models](http://i.ytimg.com/vi/zjkBMFhNj_g/mqdefault.jpg)
![[1hr Talk] Intro to Large Language Models](/img/tr.png)
You are automating the automation ! Thank you for your efforts. 🙏
Thank you too!
this is so freaking cool , a local setup to recursively refine and critique such generative creations would be ideal . the back and forth of loading this up into the system if made any manual changes seems to be the largest bottleneck . awesome works !
By the way, pseudo-finetuning is quite a handy expression for kind of finetuning without finetuning.
agreed, i wish we could just make up new terms to distinguish better between them. But for sure - pseudo-fine-tuning works well !