Commit History

change model loading mechanism
90c428d

zetavg commited on

do not allow using base model directly, seems that it will break things
2f0a0ce
unverified

zetavg commited on

test new defaults
d50497e
unverified

zetavg commited on

update ui
414c86a
unverified

zetavg commited on

inference beams default to 2 since it’s better
bd922de
unverified

zetavg commited on

ok
e200f8c
unverified

zetavg commited on

why
4354315
unverified

zetavg commited on

fix wrong Pillow version on colab
d954ae1
unverified

zetavg commited on

try
50ba9ae
unverified

zetavg commited on

Revert "try to fix AttributeError: module 'PIL.Image' has no attribute 'Resampling'"
1a12f0b
unverified

zetavg commited on

try to fix AttributeError: module 'PIL.Image' has no attribute 'Resampling'
d74655a
unverified

zetavg commited on

update README.md
d06bf26
unverified

zetavg commited on

Merge branch 'dev-2'
6c08b63
unverified

zetavg commited on

rename project
bbdf699
unverified

zetavg commited on

add templates/user_and_ai.json
faa8dd3
unverified

zetavg commited on

move to latest working version of peft
fe7c9d2

zetavg commited on

cache lora models
966795b

zetavg commited on

load base model on start
fa0947b
unverified

zetavg commited on

fix inference prompt preview not updated to the latest version
e3a5631
unverified

zetavg commited on

resolve generation canceling issue
883e16a

zetavg commited on

report status while finetune starting
4623b35

zetavg commited on

auto select prompt template for model
517781a
unverified

zetavg commited on

save train info with model
fb9b56d

zetavg commited on

clear cache after training
dba0ad5

zetavg commited on

update README.md
4c02e18
unverified

zetavg commited on

fix “AttributeError: module 'PIL.Image' has no attribute 'Resampling'”
60ce564
unverified

zetavg commited on

cache loaded_base_model_with_lora
49b832f
unverified

zetavg commited on

update requirements.lock.txt
d047590
unverified

zetavg commited on

latest peft makes model.save_pretrained in finetune.py save a 443 B adapter_model.bin which is clearly incorrect (normally adapter_model.bin should > 16 MB)
7dd8f96
unverified

zetavg commited on

update requirements.lock.txt
3391607
unverified

zetavg commited on

update requirements.lock.txt
19e630b
unverified

zetavg commited on

try to lock requirements
69acddc
unverified

zetavg commited on

fix
b9929ef
unverified

zetavg commited on

Merge branch 'main' of github.com:zetavg/llama-lora
ea16ea2
unverified

zetavg commited on

this should be set for training
7b14813
unverified

zetavg commited on

Update README.md
bd0584c
unverified

Pokai Chang commited on

some fixes
c15d0e4
unverified

zetavg commited on

update README.md
f31c4d4
unverified

zetavg commited on

Merge branch 'dev-2'
490219f
unverified

zetavg commited on

update README.md and LLaMA_LoRA.ipynb
d803879
unverified

zetavg commited on

update
9279c83
unverified

zetavg commited on

update finetune
8788753
unverified

zetavg commited on

simulate actual behavior in ui dev mode
5929f2a
unverified

zetavg commited on

update default branch to main
e55a664
unverified

zetavg commited on

fix possible error
0c97f91
unverified

zetavg commited on

fix “RuntimeError: expected scalar type Half but found Float” on lambdalabs and hf
4b2400e
unverified

zetavg commited on

update
116804a
unverified

zetavg commited on

add cancel timeout buttons and update ui
320751d
unverified

zetavg commited on

update ui
3a38e1d
unverified

zetavg commited on

ui fix
1cb2b40
unverified

zetavg commited on