qwerrwe / src

Commit History

Lint callbacks.py
5062eca

Nanobit commited on

Lint prompters.py
cb4f0e9

Nanobit commited on

Refactor
4c0eddb

Nanobit commited on

Lint flash_attn.py
1c60c10

Nanobit commited on

Fix lint
903ea30

Nanobit commited on

Fix data.py lint
cb7cd34

Nanobit commited on

Lint and format
392dfd9

Nanobit commited on

fix relative path for fixtures
e65aeed

winglian commited on

refactor conversation plucking in sharegpt
21c8e2d

winglian commited on

new hf_use_auth_token setting so login to hf isn't required
1c33eb8

winglian commited on

Feat: Update validate_config and add tests
52dd92a

Nanobit commited on

Apply black formatter
7bf2069

Nanobit commited on

refactor: fix previous refactors
56f9ca5

Nanobit commited on

Refactor to use DictDefault instead
8bd7a49

Nanobit commited on

Add DictDefault
18d41ce

Nanobit commited on

Convert attrdict to addict
bdfe7c9

Nanobit commited on

Merge pull request #67 from OpenAccess-AI-Collective/refactor-tokenizer-load
0d4a7f4
unverified

winglian commited on

Merge pull request #86 from OpenAccess-AI-Collective/NanoCode012-warning-remote-code
782996d
unverified

Nanobit commited on

Fix: Remove base class inherit for CompletionPrompter
9ac1884
unverified

Nanobit commited on

Add warning for `trust_remote_code`
2824423
unverified

Nanobit commited on

Merge branch 'main' into refactor/rename-4b-to-gptq
147241c
unverified

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(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

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

Nanobit commited on

Fix recommendation condition
fe0e69f
unverified

Nanobit commited on

load the tokenizer seperately from the model
32e6fe9

winglian commited on

Add cfg.lora_target_linear
9196237

Nanobit 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 merge conflict failure, black format
7b5e762

winglian commited on

fixes to make qlora actually work
34c99f9

winglian commited on

another fix for shard and train split
2e56203

winglian commited on

shard fix
ac79360

winglian commited on

missed ...
943961f

winglian commited on

change auth token setting back
d2a6f79

winglian commited on

Update src/axolotl/prompters.py
0048202
unverified

winglian Nanobit 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 #55 from OpenAccess-AI-Collective/missing-validation-file
de2a733
unverified

winglian commited on

add missing file
1d7da3b

winglian commited on

stray s
f523a08

winglian commited on

cfg.cfg fix, also de-dupe lora module list
676d7da

winglian commited on

fix tuple add to list
a8771b0

winglian commited on

Update src/axolotl/utils/models.py
1cf21da
unverified

winglian Nanobit commited on

attempt to find linear modules for qlora
ffd1043

winglian commited on