Wing Lian
|
1987e5cf56
|
qlora and 4bit check so we are able to merge and unload
|
2023-05-25 22:55:13 -04:00 |
|
Wing Lian
|
e7e1a777bd
|
fix bool args according to python fire docs
|
2023-05-25 22:45:41 -04:00 |
|
Wing Lian
|
7b5e762be2
|
fix merge conflict failure, black format
|
2023-05-25 22:40:27 -04:00 |
|
Wing Lian
|
3f6017db9e
|
qlora merge and load requires that base model isn't loaded in 4 or 8 bit
|
2023-05-25 22:39:13 -04:00 |
|
Wing Lian
|
34c99f9812
|
fixes to make qlora actually work
|
2023-05-25 22:37:23 -04:00 |
|
Wing Lian
|
259262bf42
|
fix xentropy wheel name typo
|
2023-05-25 17:25:38 -04:00 |
|
Wing Lian
|
2e56203b50
|
another fix for shard and train split
|
2023-05-25 17:23:57 -04:00 |
|
Wing Lian
|
be3d3963cd
|
Merge pull request #58 from OpenAccess-AI-Collective/shards-fix
shard fix
|
2023-05-25 16:32:31 -04:00 |
|
Wing Lian
|
ac79360161
|
shard fix
|
2023-05-25 16:31:59 -04:00 |
|
Wing Lian
|
b2fb61845e
|
Merge pull request #54 from OpenAccess-AI-Collective/winglian-patch-1
add discord link to #axolotl-help channel
|
2023-05-25 12:45:19 -04:00 |
|
Wing Lian
|
71d600fc43
|
Merge branch 'main' into winglian-patch-1
|
2023-05-25 12:45:13 -04:00 |
|
Wing Lian
|
4fd0c2d1b9
|
Merge pull request #57 from OpenAccess-AI-Collective/fixes-for-basic-samples
fixes w/ example for super basic lora starter
|
2023-05-25 12:43:22 -04:00 |
|
Wing Lian
|
943961fd10
|
missed ...
|
2023-05-25 12:42:56 -04:00 |
|
Wing Lian
|
d2a6f79fd1
|
change auth token setting back
|
2023-05-25 12:41:17 -04:00 |
|
Wing Lian
|
98b1bce57e
|
pr comments addressed
|
2023-05-25 12:25:07 -04:00 |
|
Wing Lian
|
004820209d
|
Update src/axolotl/prompters.py
Co-authored-by: NanoCode012 <kevinvong@rocketmail.com>
|
2023-05-25 12:21:02 -04:00 |
|
Wing Lian
|
8d6a28953f
|
fix relative path in flash-attn build:
|
2023-05-25 12:18:28 -04:00 |
|
Wing Lian
|
e396654319
|
fix tokenizer loading, got openllama 3b working
|
2023-05-25 12:15:12 -04:00 |
|
Wing Lian
|
a5d739b66b
|
fixes w/ example for super basic lora starter
|
2023-05-25 11:59:08 -04:00 |
|
Wing Lian
|
951facbb1f
|
Merge pull request #56 from OpenAccess-AI-Collective/fix-build-flash-attn
fix cd within flash-attn
|
2023-05-25 11:29:47 -04:00 |
|
Wing Lian
|
f5fa3d131b
|
fix cd within flash-attn
|
2023-05-25 11:29:15 -04:00 |
|
NanoCode012
|
7ec105041d
|
Merge pull request #48 from NanoCode012/feat/update-readme
Feat: Minor update readme from dev changes
|
2023-05-25 23:49:58 +09:00 |
|
NanoCode012
|
a9e502ef45
|
Update 4bit notes
|
2023-05-25 23:48:18 +09:00 |
|
NanoCode012
|
68f0c71424
|
Merge pull request #49 from NanoCode012/feat/gitignore
Feat: Update gitignore using standard Python template
|
2023-05-25 23:42:49 +09:00 |
|
NanoCode012
|
52fb6d8a34
|
Update gitignore using standard Python template
|
2023-05-25 23:07:27 +09:00 |
|
NanoCode012
|
f92245dbd6
|
Fix missing closing code block
|
2023-05-25 23:06:33 +09:00 |
|
NanoCode012
|
e65c203e9e
|
Add more detail on minimum GPU
|
2023-05-25 23:06:33 +09:00 |
|
NanoCode012
|
1377400c33
|
Add info on Runtime Error
|
2023-05-25 23:06:33 +09:00 |
|
NanoCode012
|
2c34f8d0c7
|
Update dataset type
|
2023-05-25 23:06:33 +09:00 |
|
NanoCode012
|
7bc28eb8a8
|
Add more data formats
|
2023-05-25 23:06:33 +09:00 |
|
NanoCode012
|
29273b5a5b
|
Add other minor configs
|
2023-05-25 23:06:33 +09:00 |
|
NanoCode012
|
05c18340d6
|
Update scheduler configs
|
2023-05-25 23:06:33 +09:00 |
|
NanoCode012
|
5b712afbe4
|
Update bf16 options
|
2023-05-25 23:06:33 +09:00 |
|
NanoCode012
|
9083910036
|
Update lora config
|
2023-05-25 23:06:33 +09:00 |
|
NanoCode012
|
8552218491
|
Improve Inference instruction
|
2023-05-25 23:06:33 +09:00 |
|
Wing Lian
|
de2a7335e6
|
Merge pull request #55 from OpenAccess-AI-Collective/missing-validation-file
add missing file
|
2023-05-25 09:58:51 -04:00 |
|
Wing Lian
|
1d7da3b389
|
add missing file
|
2023-05-25 09:58:29 -04:00 |
|
Wing Lian
|
e07bd8a441
|
add discord link to #axolotl-help channel
|
2023-05-25 09:45:45 -04:00 |
|
Wing Lian
|
d092cdb19b
|
Merge pull request #52 from OpenAccess-AI-Collective/bugfix-cfg-cfg
cfg.cfg fix, also de-dupe lora module list
|
2023-05-25 09:35:24 -04:00 |
|
Wing Lian
|
f523a0894c
|
stray s
|
2023-05-25 09:23:56 -04:00 |
|
Wing Lian
|
676d7da661
|
cfg.cfg fix, also de-dupe lora module list
|
2023-05-25 09:18:57 -04:00 |
|
Wing Lian
|
a617f1b65e
|
Merge pull request #44 from OpenAccess-AI-Collective/qlora-add-modules-tuple
fix tuple add to list
|
2023-05-24 23:46:40 -04:00 |
|
Wing Lian
|
a8771b0aad
|
fix tuple add to list
|
2023-05-24 23:46:04 -04:00 |
|
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 |
|