Commit History

make gradio reload faster by using dynamic imports
8b0ae10
unverified

zetavg commited on

extract configs from global
40a8f4e
unverified

zetavg commited on

improve speed of switching models by offloading unused ones to cpu ram instead if unloading
6148b7c
unverified

zetavg commited on

support switching to custom tokenizer
0054cc5
unverified

zetavg commited on

support --trust_remote_code, resolves #6
03b5741

zetavg commited on

support switching base models
fd15ecb

zetavg commited on

add wandb support
a5d7977

zetavg commited on

preload base model on colab
a1771a7
unverified

zetavg commited on

change model loading mechanism
90c428d

zetavg commited on

rename project
bbdf699
unverified

zetavg commited on

cache lora models
966795b

zetavg commited on

resolve generation canceling issue
883e16a

zetavg commited on

cache loaded_base_model_with_lora
49b832f
unverified

zetavg commited on

some fixes
c15d0e4
unverified

zetavg commited on

update
9279c83
unverified

zetavg commited on

update
35fba55
unverified

zetavg commited on

update
87a0e23
unverified

zetavg commited on

let finetune ui support showing training progress
9ee06c7
unverified

zetavg commited on

work on finetune ui
49ce4b9
unverified

zetavg commited on

ui updates
72ff821
unverified

zetavg commited on

add inference_ui and stuff
d754e91
unverified

zetavg commited on

init
82f1bf5
unverified

zetavg commited on