Wing Lian
|
cf48ff7cac
|
Merge pull request #41 from OpenAccess-AI-Collective/qlora-modules
attempt to find linear modules for qlora
|
2023-05-24 23:31:19 -04:00 |
|
Wing Lian
|
1cf21daf51
|
Update src/axolotl/utils/models.py
Co-authored-by: NanoCode012 <kevinvong@rocketmail.com>
|
2023-05-24 23:31:12 -04:00 |
|
Wing Lian
|
ffd1043607
|
attempt to find linear modules for qlora
|
2023-05-24 23:18:08 -04:00 |
|
Wing Lian
|
3369c4dcf8
|
Merge pull request #39 from OpenAccess-AI-Collective/dev
Dev to main
|
2023-05-24 23:03:22 -04:00 |
|
Wing Lian
|
bc97f9c584
|
remove dev specific remark
|
2023-05-24 23:00:53 -04:00 |
|
Wing Lian
|
ce34d64e8a
|
apply black formatting
|
2023-05-24 22:59:33 -04:00 |
|
Wing Lian
|
ce694e20a3
|
Merge branch 'main' of github.com:OpenAccess-AI-Collective/axolotl into dev
|
2023-05-24 22:59:09 -04:00 |
|
Wing Lian
|
cebea372da
|
Merge pull request #36 from OpenAccess-AI-Collective/qlora
Qlora
|
2023-05-24 22:57:37 -04:00 |
|
Wing Lian
|
1f5d83ea72
|
remove un-needed code, add validation
|
2023-05-24 22:47:43 -04:00 |
|
Wing Lian
|
6e7d4d5344
|
Merge pull request #35 from NanoCode012/update-readme
Feat: Rewrite Readme
|
2023-05-24 21:31:32 -04:00 |
|
NanoCode012
|
362821ce84
|
Add trust_remote_code config
|
2023-05-25 09:53:49 +09:00 |
|
NanoCode012
|
224d186ec9
|
Simplify docker instruction
|
2023-05-25 09:51:22 +09:00 |
|
NanoCode012
|
5417824b31
|
Add seq length
|
2023-05-25 09:50:43 +09:00 |
|
NanoCode012
|
e1a91b0918
|
Remove redundant formats
|
2023-05-25 09:48:18 +09:00 |
|
NanoCode012
|
2a1b5728e6
|
Add line break
|
2023-05-25 09:37:18 +09:00 |
|
NanoCode012
|
702f2eee4b
|
Fix inference command
|
2023-05-25 09:36:33 +09:00 |
|
NanoCode012
|
88bba24d9e
|
Clean up data readme
|
2023-05-25 09:34:35 +09:00 |
|
NanoCode012
|
ba9ac723f1
|
Update quickstart. Add common error and contribution section.
|
2023-05-25 09:32:04 +09:00 |
|
NanoCode012
|
db73b94a58
|
Add image. Add quickstart. Simplify dataset.
|
2023-05-25 09:32:04 +09:00 |
|
NanoCode012
|
00dfe43b1d
|
Add image
|
2023-05-25 09:32:04 +09:00 |
|
NanoCode012
|
9aab0b8cfe
|
Update Docker instructions
|
2023-05-25 09:32:04 +09:00 |
|
NanoCode012
|
857a80b70e
|
Format dataset types
|
2023-05-25 09:32:04 +09:00 |
|
NanoCode012
|
cba0048067
|
Update typo
|
2023-05-25 09:32:04 +09:00 |
|
NanoCode012
|
c22df8db9b
|
Add all dataset types
|
2023-05-25 09:32:04 +09:00 |
|
NanoCode012
|
68237ea90a
|
Add extra note to Readme
|
2023-05-25 09:32:04 +09:00 |
|
NanoCode012
|
4ee79f2641
|
Fix typo
|
2023-05-25 09:32:04 +09:00 |
|
NanoCode012
|
2b436680a0
|
Add new config options to Readme
|
2023-05-25 09:32:04 +09:00 |
|
NanoCode012
|
04d281312c
|
Feat: Rewrite Readme
|
2023-05-25 09:32:04 +09:00 |
|
Wing Lian
|
7e81ca720b
|
Update requirements.txt
Co-authored-by: NanoCode012 <kevinvong@rocketmail.com>
|
2023-05-24 15:44:48 -04:00 |
|
Wing Lian
|
3960936bf7
|
Merge pull request #37 from Thytu/main
fix: handles AutoTokenizer from untrusted source
|
2023-05-24 15:42:41 -04:00 |
|
Valentin De Matos
|
88ad05df54
|
fix: handles AutoTokenizer from untrusted source
Set trust_remote_code param depending of cfg.trust_remote_code when calling AutoTokenizer.from_pretrained
|
2023-05-24 20:57:10 +02:00 |
|
Wing Lian
|
e8aacfbd7c
|
more qlora support
|
2023-05-24 14:33:18 -04:00 |
|
Wing Lian
|
b9d07aa95a
|
prepare does all this already for qlora?
|
2023-05-24 14:32:39 -04:00 |
|
Wing Lian
|
3b4d055edd
|
integrate qlora? maybe?
|
2023-05-24 14:32:39 -04:00 |
|
Wing Lian
|
2ae936fbc4
|
fix missing fp16 kwarg
|
2023-05-23 20:44:24 -04:00 |
|
Wing Lian
|
fb100a9ee1
|
fix enum pass as value
|
2023-05-23 11:34:03 -04:00 |
|
Wing Lian
|
3a503770e4
|
Add qa style data for alpaca instructions, fix one_cycle scheduler
|
2023-05-22 22:58:10 -04:00 |
|
Wing Lian
|
b029a11e65
|
Merge pull request #34 from OpenAccess-AI-Collective/dev-unstable
lots of various improvements
|
2023-05-22 12:14:56 -04:00 |
|
Wing Lian
|
e3df3a9f5d
|
cuda/pytorch matrix builds
|
2023-05-22 12:14:21 -04:00 |
|
Wing Lian
|
f950a881e1
|
cuda, pytorch matrix for base builds
|
2023-05-22 12:12:08 -04:00 |
|
Wing Lian
|
de6da13e19
|
don't need to set here
|
2023-05-22 12:12:01 -04:00 |
|
Wing Lian
|
9493b1b137
|
be able to use adam bnb 8bit and one cycle scheduler w fsdp
|
2023-05-22 09:00:49 -04:00 |
|
Wing Lian
|
1b3e401241
|
Update src/axolotl/utils/models.py for info msg
Co-authored-by: NanoCode012 <kevinvong@rocketmail.com>
|
2023-05-21 23:01:35 -04:00 |
|
Wing Lian
|
3457810988
|
Update scripts/finetune.py
Co-authored-by: NanoCode012 <kevinvong@rocketmail.com>
|
2023-05-21 23:00:28 -04:00 |
|
Wing Lian
|
ae1719d30c
|
Update scripts/finetune.py for logging
Co-authored-by: NanoCode012 <kevinvong@rocketmail.com>
|
2023-05-21 23:00:23 -04:00 |
|
Wing Lian
|
98a6781f18
|
Update src/axolotl/utils/data.py for spelling
Co-authored-by: NanoCode012 <kevinvong@rocketmail.com>
|
2023-05-21 23:00:13 -04:00 |
|
Wing Lian
|
607a4d33f2
|
make sure to use train split if loading from hf
|
2023-05-21 22:04:39 -04:00 |
|
Wing Lian
|
99383f14a3
|
make one cycle lr div factor configurable
|
2023-05-21 20:25:06 -04:00 |
|
Wing Lian
|
0f74464652
|
fix new dataset prompt tokenizers
|
2023-05-21 18:57:09 -04:00 |
|
Wing Lian
|
e0602a9e54
|
add missing __init__
|
2023-05-21 16:36:41 -04:00 |
|