NanoCode012
|
ed2dd77e35
|
Merge pull request #89 from OpenAccess-AI-Collective/NanoCode012-update-action-version
Feat: Update actions version
|
2023-05-28 02:12:26 +09:00 |
|
NanoCode012
|
2b8c28bab8
|
Update actions version
|
2023-05-28 01:51:10 +09:00 |
|
NanoCode012
|
782996d94a
|
Merge pull request #86 from OpenAccess-AI-Collective/NanoCode012-warning-remote-code
Feat: Add warning for `trust_remote_code`
|
2023-05-28 01:29:35 +09:00 |
|
NanoCode012
|
b50d7d311c
|
Merge pull request #88 from OpenAccess-AI-Collective/NanoCode012-completion-prompter-no-inherit
Fix: Remove base class inherit for CompletionPrompter
|
2023-05-28 01:29:03 +09:00 |
|
Wing Lian
|
35af017001
|
Merge pull request #87 from OpenAccess-AI-Collective/add_prompter_tests
automated testing in github actions
|
2023-05-27 12:21:23 -04:00 |
|
Wing Lian
|
a653392287
|
use requirements file for tests
|
2023-05-27 12:17:46 -04:00 |
|
Wing Lian
|
72b6ca0d9f
|
cache pip
|
2023-05-27 12:16:54 -04:00 |
|
Wing Lian
|
7f53fd2ab6
|
alright, just local install it
|
2023-05-27 12:16:06 -04:00 |
|
Wing Lian
|
c29d33352c
|
move python path to same step as tests
|
2023-05-27 12:06:23 -04:00 |
|
Wing Lian
|
403af0b1d7
|
fix path and streamline pip installs
|
2023-05-27 11:58:37 -04:00 |
|
NanoCode012
|
9ac1884323
|
Fix: Remove base class inherit for CompletionPrompter
|
2023-05-28 00:51:35 +09:00 |
|
Wing Lian
|
d199d6c261
|
automated testing in github actions
|
2023-05-27 11:51:01 -04:00 |
|
NanoCode012
|
2824423d10
|
Add warning for trust_remote_code
|
2023-05-28 00:46:56 +09:00 |
|
NanoCode012
|
cb18856fc2
|
Merge pull request #85 from NanoCode012/fix/add-dataset-shard-readme
Feat: Add `dataset_shard_num` and `dataset_shard_idx` to Readme
|
2023-05-27 23:52:50 +09:00 |
|
NanoCode012
|
8626b54aab
|
Add dataset_shard_num and dataset_shard_idx
|
2023-05-27 23:51:17 +09:00 |
|
Wing Lian
|
87dffbc451
|
Merge pull request #75 from Thytu/refactor/rename-4b-to-gptq
refactor: change 4bit nomenclature to gptq
|
2023-05-27 09:37:57 -04:00 |
|
Wing Lian
|
147241ca66
|
Merge branch 'main' into refactor/rename-4b-to-gptq
|
2023-05-27 09:37:52 -04:00 |
|
Wing Lian
|
7e974decb7
|
Merge pull request #76 from OpenAccess-AI-Collective/truthy-validation
Truthy validation
|
2023-05-27 09:36:10 -04:00 |
|
Wing Lian
|
11fd39b1f5
|
Merge pull request #78 from OpenAccess-AI-Collective/falcoln-support
falcon: sane starter defaults and add lora support
|
2023-05-27 09:35:56 -04:00 |
|
Wing Lian
|
157420df13
|
sane starter defaults and add lora
|
2023-05-27 09:33:14 -04:00 |
|
Wing Lian
|
679ffd7395
|
Merge pull request #77 from OpenAccess-AI-Collective/falcoln-support
add example for falcon support
|
2023-05-27 09:18:48 -04:00 |
|
Wing Lian
|
d5f944ce2a
|
add example for falcoln support
|
2023-05-27 09:16:43 -04:00 |
|
Wing Lian
|
4c906339f7
|
fix auto linear modules for lora w/o any set already
|
2023-05-27 08:49:43 -04:00 |
|
Wing Lian
|
4c500f5830
|
checking for False is not sufficent for NoneType/unset configs
|
2023-05-27 08:43:48 -04:00 |
|
Thytu
|
7cf07fc8b3
|
refactor(example): rename 4bit-lora-7b by gptq-lora-7b
Signed-off-by: Thytu <vdmatos@gladia.io>
|
2023-05-27 12:37:53 +00:00 |
|
Thytu
|
dd0065773a
|
refactor(param): rename load_4bit config param by gptq
Signed-off-by: Thytu <vdmatos@gladia.io>
|
2023-05-27 12:36:03 +00:00 |
|
Wing Lian
|
c3d256271e
|
fix wheel install glob
|
2023-05-26 10:37:02 -04:00 |
|
NanoCode012
|
46c5a44003
|
Merge pull request #69 from OpenAccess-AI-Collective/NanoCode012-quickstart-disable-xformers
Fix: Disable xformers for QuickStart config
|
2023-05-26 22:40:16 +09:00 |
|
NanoCode012
|
ec3c0314bf
|
Merge pull request #65 from NanoCode012/feat/target-linear
Feat: Add `cfg.lora_target_linear`
|
2023-05-26 22:39:38 +09:00 |
|
NanoCode012
|
79560934f9
|
Disable formers for QuickStart config
|
2023-05-26 22:23:38 +09:00 |
|
NanoCode012
|
353cebd838
|
Merge pull request #68 from OpenAccess-AI-Collective/NanoCode012-patch-1
Fix: Incorrect recommendation condition
|
2023-05-26 22:20:31 +09:00 |
|
NanoCode012
|
fe0e69f4f9
|
Fix recommendation condition
|
2023-05-26 22:19:50 +09:00 |
|
Wing Lian
|
1fc9b44e3d
|
fix wheel blobs in dockerfile
|
2023-05-26 07:40:11 -04:00 |
|
NanoCode012
|
919623793a
|
Add cfg.lora_target_linear
|
2023-05-26 14:32:30 +09:00 |
|
Wing Lian
|
bbfc333a01
|
Merge pull request #62 from OpenAccess-AI-Collective/qlora-fixes
Qlora fixes
|
2023-05-26 00:28:16 -04:00 |
|
Wing Lian
|
a5bf838685
|
add logging and make sure model unloads to float16
|
2023-05-26 00:09:55 -04:00 |
|
Wing Lian
|
a4f12415a0
|
update readme and add typehints
|
2023-05-25 23:10:11 -04:00 |
|
Wing Lian
|
48f4c0571e
|
fix validation for qlora merge
|
2023-05-25 23:02:03 -04:00 |
|
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 |
|
NanoCode012
|
3815c054b6
|
Merge pull request #61 from NanoCode012/feat/update-readme
Feat: Update readme
|
2023-05-26 11:27:31 +09:00 |
|
NanoCode012
|
85326bfbf3
|
Update quickstart config
|
2023-05-26 11:15:57 +09:00 |
|
NanoCode012
|
e689069afd
|
Add xformers error
|
2023-05-26 11:12:03 +09:00 |
|
NanoCode012
|
d7d8bc739e
|
Add strict yml
|
2023-05-26 11:10:59 +09:00 |
|
NanoCode012
|
60e32ff457
|
Fix shard config
|
2023-05-26 11:09:28 +09:00 |
|
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 |
|