Ar57m

Adds a way of merging models with different sizes(B)

7

I'm adding the possibility of merging models with different amounts of parameters(Bs) which have the same amount of layers, through task arithmetic. I kinda hardcoded generalized task arithmetic to make...

Maybe something wrong with custom model

4

it appears that the app wants 2 tokenizer_config.json in the same folder, which is impossible. On presentation/src/main/java/com/shifthackz/aisdv1/presentation/screen/setup/ServerSetupScreen.kt line 618 do you mean vocab.json?  Another question, I converted to...

Adds a new method to shuffle/swap values

5

in each tensor. I'm bad at describing what it does, so here's the exact function in a code to serve as an example/demo. ``` import torch x = torch.arange(2, 2*6*4...

can you guys implement it on the app mlcchat as llama.cpp? cause in low ram devices it crashes instantly when trying to generate text