Hugging Face's logo

Spaces:
Dovakiins
/
qwerrwe
Build error

App Files Community
qwerrwe / src /axolotl /utils /models.py

Commit History

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

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

load the tokenizer seperately from the model
32e6fe9

winglian commited on

Add cfg.lora_target_linear
9196237

Nanobit 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

fix tokenizer loading, got openllama 3b working
e396654

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

apply black formatting
ce34d64

winglian commited on

Merge branch 'main' of github.com:OpenAccess-AI-Collective/axolotl into dev
ce694e2

winglian commited on

remove un-needed code, add validation
1f5d83e

winglian commited on

fix: handles AutoTokenizer from untrusted source
88ad05d
unverified

Valentin De Matos commited on

more qlora support
e8aacfb

winglian commited on

prepare does all this already for qlora?
b9d07aa

winglian commited on

integrate qlora? maybe?
3b4d055

winglian commited on

Update src/axolotl/utils/models.py for info msg
1b3e401
unverified

winglian Nanobit commited on

tokenization fixes
4ea9a66

winglian commited on

optionally be able to specify alpaca or chat style prompts
1d5ab84

winglian commited on

Set `half` using `cfg.fp16` for 4bit
641f801
unverified

Nanobit commited on

support for replit lm
8c2f3cb

winglian commited on

Add `lora_modules_to_save`
2c73c81
unverified

Nanobit commited on

more fixes
bdbca8f

winglian commited on

more fixes
42410c7

winglian commited on

fix torch_dtype for model load
aef00b6

winglian commited on

optimize dataloading to use cache, fix model token embedding sizes
aa3c3f9

winglian commited on

black formatting
2bc1a5b

winglian commited on

various fixes
7a490a4

winglian commited on

testing mpt triton
e2e68c3

winglian commited on

add support for trust_remote_code for mpt models
a125693

winglian commited on

refactor inference, warn if model is frozen
247825b

winglian commited on

fix adam bnb optimizer grouped parameters, fix peft model 8bit conversion logic, black formatting
7748f3d

winglian commited on

support llama-adapter zero init attention
2255bb7

winglian commited on

fdsp config dict fix, todo list, add torchdistx support
ad2b48c

winglian commited on

8bit and deepspeed changes
9190ada

winglian commited on

don't load models in 8bit unless they are using an adapter, also fix tokenizer load in exceptional case
6dfdd2d

winglian commited on

fix sharegpt tokenization, refactor tokenization debugging
5159d00

winglian commited on

fix dataset handling, support galactica
4a17a4c

winglian commited on

tweaks to data loading, 8 bit adam, accelerate and deepspeed
097d367

winglian commited on

shuffle and split dataset after save/load
4f2584f

winglian commited on

fix sharegpt handling from hf, don't worry about loading llama if using earlier transformers release
8d43785

winglian commited on

various bugfixes
94f5e41

winglian commited on

fix bug when model_type not explicitly passed
bb991fd

winglian commited on