Commit History
fix auto linear modules for lora w/o any set already
4c90633
checking for False is not sufficent for NoneType/unset configs
4c500f5
refactor(param): rename load_4bit config param by gptq
dd00657
Thytu
commited on
Merge pull request #65 from NanoCode012/feat/target-linear
ec3c031
unverified
Fix recommendation condition
fe0e69f
unverified
Add cfg.lora_target_linear
9196237
add logging and make sure model unloads to float16
a5bf838
update readme and add typehints
a4f1241
fix validation for qlora merge
48f4c05
qlora and 4bit check so we are able to merge and unload
1987e5c
fix merge conflict failure, black format
7b5e762
fixes to make qlora actually work
34c99f9
another fix for shard and train split
2e56203
shard fix
ac79360
missed ...
943961f
change auth token setting back
d2a6f79
fix tokenizer loading, got openllama 3b working
e396654
fixes w/ example for super basic lora starter
a5d739b
Merge pull request #55 from OpenAccess-AI-Collective/missing-validation-file
de2a733
unverified
add missing file
1d7da3b
stray s
f523a08
cfg.cfg fix, also de-dupe lora module list
676d7da
fix tuple add to list
a8771b0
attempt to find linear modules for qlora
ffd1043
apply black formatting
ce34d64
Merge branch 'main' of github.com:OpenAccess-AI-Collective/axolotl into dev
ce694e2
remove un-needed code, add validation
1f5d83e
fix: handles AutoTokenizer from untrusted source
88ad05d
unverified
Valentin De Matos
commited on