Commit History

use quantization config
8b0674e

emya commited on

cpu offload option
f87d353

emya commited on

import torch
6cc14e5

emya commited on

add dtype
5f03bba

emya commited on

add scipy
b77e308

emya commited on

add bitsandbytes
ec75fc5

emya commited on

add accelerate
47dd5c9

emya commited on

use base and new models
2f9c1ea

emya commited on

use 8bit model
8ad2f92

emya commited on

add torch into requirement
54673f1

emya commited on

add requirements
8b87148

emya commited on

Add application file
d0b3af7

emya commited on

initial commit
e3da9e1

emya commited on