On: Show HN: Promptr, let GPT operate on your codebase and other useful goodies

[MacsHeadroom]

I use Vicuna[0]. It's much better than GPT4All.

Vicuna is based on 13B (not 7B) and its training data includes humans chatting with GPT-4 vs GPT4All's purely synthetic dataset generated by GPT-3.5.

[0] https://github.com/lm-sys/FastChat

[nico → MacsHeadroom]

Thank you!

Could Vicuña be used to further fine-tune GPT4All to make it better?

[MacsHeadroom → nico]

I think GPT4All's inferior quality dataset would make a worse combined model than strict Vicuna. Vicuna-30B will likely be better than GPT-3.5 level and approaching GPT-4 level when it's done training, but run slow on CPU.