Hugging Face's logo

Spaces:
Dovakiins
/
qwerrwe
Build error

App Files Community
qwerrwe

Commit History

Merge pull request #78 from OpenAccess-AI-Collective/falcoln-support
11fd39b
unverified

winglian commited on

sane starter defaults and add lora
157420d

winglian commited on

Merge pull request #77 from OpenAccess-AI-Collective/falcoln-support
679ffd7
unverified

winglian commited on

add example for falcoln support
d5f944c

winglian commited on

fix auto linear modules for lora w/o any set already
4c90633

winglian commited on

checking for False is not sufficent for NoneType/unset configs
4c500f5

winglian commited on

refactor(example): rename 4bit-lora-7b by gptq-lora-7b
7cf07fc

Thytu commited on

refactor(param): rename load_4bit config param by gptq
dd00657

Thytu commited on

Update src/axolotl/utils/models.py
ca1bb92
unverified

winglian Nanobit commited on

Update src/axolotl/utils/models.py
933e970
unverified

winglian Nanobit commited on

fix wheel install glob
c3d2562

winglian commited on

Merge pull request #69 from OpenAccess-AI-Collective/NanoCode012-quickstart-disable-xformers
46c5a44
unverified

Nanobit commited on

Merge pull request #65 from NanoCode012/feat/target-linear
ec3c031
unverified

Nanobit commited on

Disable formers for QuickStart config
7956093
unverified

Nanobit commited on

Merge pull request #68 from OpenAccess-AI-Collective/NanoCode012-patch-1
353cebd
unverified

Nanobit commited on

Fix recommendation condition
fe0e69f
unverified

Nanobit commited on

fix wheel blobs in dockerfile
1fc9b44

winglian commited on

load the tokenizer seperately from the model
32e6fe9

winglian commited on

Add cfg.lora_target_linear
9196237

Nanobit commited on

Merge pull request #62 from OpenAccess-AI-Collective/qlora-fixes
bbfc333
unverified

winglian commited on

add logging and make sure model unloads to float16
a5bf838

winglian commited on

update readme and add typehints
a4f1241

winglian commited on

fix validation for qlora merge
48f4c05

winglian commited on

qlora and 4bit check so we are able to merge and unload
1987e5c

winglian commited on

fix bool args according to python fire docs
e7e1a77

winglian commited on

fix merge conflict failure, black format
7b5e762

winglian commited on

qlora merge and load requires that base model isn't loaded in 4 or 8 bit
3f6017d

winglian commited on

fixes to make qlora actually work
34c99f9

winglian commited on

Merge pull request #61 from NanoCode012/feat/update-readme
3815c05
unverified

Nanobit commited on

Update quickstart config
85326bf

Nanobit commited on

Add xformers error
e689069

Nanobit commited on

Add strict yml
d7d8bc7

Nanobit commited on

Fix shard config
60e32ff

Nanobit commited on

fix xentropy wheel name typo
259262b

winglian commited on

another fix for shard and train split
2e56203

winglian commited on

Merge pull request #58 from OpenAccess-AI-Collective/shards-fix
be3d396
unverified

winglian commited on

shard fix
ac79360

winglian commited on

Merge pull request #54 from OpenAccess-AI-Collective/winglian-patch-1
b2fb618
unverified

winglian commited on

Merge branch 'main' into winglian-patch-1
71d600f
unverified

winglian commited on

Merge pull request #57 from OpenAccess-AI-Collective/fixes-for-basic-samples
4fd0c2d
unverified

winglian commited on

missed ...
943961f

winglian commited on

change auth token setting back
d2a6f79

winglian commited on

pr comments addressed
98b1bce

winglian commited on

Update src/axolotl/prompters.py
0048202
unverified

winglian Nanobit commited on

fix relative path in flash-attn build:
8d6a289

winglian commited on

fix tokenizer loading, got openllama 3b working
e396654

winglian commited on

fixes w/ example for super basic lora starter
a5d739b

winglian commited on

Merge pull request #56 from OpenAccess-AI-Collective/fix-build-flash-attn
951facb
unverified

winglian commited on

fix cd within flash-attn
f5fa3d1

winglian commited on

Merge pull request #48 from NanoCode012/feat/update-readme
7ec1050
unverified

Nanobit commited on