ceos/unsloth
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
624 commits 391 branches 58 tags 304 MiB
Commit graph

624 commits

This branch
This branch
All branches
Author SHA1 Message Date
Daniel Han
9ca13b836f Update _utils.py 2024-10-24 12:17:48 -07:00
Daniel Han
9ca0bba14b
 		Fix 4.47 issue (#1182) 
* Fix TRL

* Update mistral.py

* Patch processing_class

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Installation guide (#1165)

* chore: update chat_templates.py (#1166)

orginal -> original

* Disable Flex Attention

* Update tokenizer_utils.py

* Update _utils.py

* n_items

* Update cross_entropy_loss.py

* Fix DPO, ORPO

* Update _utils.py

* Update _utils.py

* fix/transformers-unpack (#1180)

* Fix DPO, ORPO (#1177)

* Fix TRL

* Update mistral.py

* Patch processing_class

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Installation guide (#1165)

* chore: update chat_templates.py (#1166)

orginal -> original

* Disable Flex Attention

* Update tokenizer_utils.py

* Update _utils.py

* n_items

* Update cross_entropy_loss.py

* Fix DPO, ORPO

* Update _utils.py

---------

Co-authored-by: timothelaborie <97834767+timothelaborie@users.noreply.github.com>
Co-authored-by: Ikko Eltociear Ashimine <eltociear@gmail.com>

* Add warning for missing Unpack and KwargsForCausalLM in older Transformers versions

---------

Co-authored-by: Daniel Han <danielhanchen@gmail.com>
Co-authored-by: timothelaborie <97834767+timothelaborie@users.noreply.github.com>
Co-authored-by: Ikko Eltociear Ashimine <eltociear@gmail.com>

* Update cross_entropy_loss.py

* Update _utils.py

* Update _utils.py

---------

Co-authored-by: timothelaborie <97834767+timothelaborie@users.noreply.github.com>
Co-authored-by: Ikko Eltociear Ashimine <eltociear@gmail.com>
Co-authored-by: Edd <68678137+Erland366@users.noreply.github.com>
 2024-10-24 12:17:21 -07:00
Daniel Han
0096e5b07f Update _utils.py 2024-10-24 12:17:09 -07:00
Daniel Han
7308bb8299 Update _utils.py 2024-10-24 12:14:14 -07:00
Daniel Han
5961c34a71 Update cross_entropy_loss.py 2024-10-24 12:11:38 -07:00
Edd
faf27477aa
 		fix/transformers-unpack (#1180) 
* Fix DPO, ORPO (#1177)

* Fix TRL

* Update mistral.py

* Patch processing_class

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Installation guide (#1165)

* chore: update chat_templates.py (#1166)

orginal -> original

* Disable Flex Attention

* Update tokenizer_utils.py

* Update _utils.py

* n_items

* Update cross_entropy_loss.py

* Fix DPO, ORPO

* Update _utils.py

---------

Co-authored-by: timothelaborie <97834767+timothelaborie@users.noreply.github.com>
Co-authored-by: Ikko Eltociear Ashimine <eltociear@gmail.com>

* Add warning for missing Unpack and KwargsForCausalLM in older Transformers versions

---------

Co-authored-by: Daniel Han <danielhanchen@gmail.com>
Co-authored-by: timothelaborie <97834767+timothelaborie@users.noreply.github.com>
Co-authored-by: Ikko Eltociear Ashimine <eltociear@gmail.com>
 2024-10-24 12:10:52 -07:00
Daniel Han
f195ee1e65 Update _utils.py 2024-10-24 01:11:20 -07:00
Daniel Han
4f1c474d4a
 		Fix DPO, ORPO (#1177) 
* Fix TRL

* Update mistral.py

* Patch processing_class

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Installation guide (#1165)

* chore: update chat_templates.py (#1166)

orginal -> original

* Disable Flex Attention

* Update tokenizer_utils.py

* Update _utils.py

* n_items

* Update cross_entropy_loss.py

* Fix DPO, ORPO

* Update _utils.py

---------

Co-authored-by: timothelaborie <97834767+timothelaborie@users.noreply.github.com>
Co-authored-by: Ikko Eltociear Ashimine <eltociear@gmail.com>
 2024-10-24 00:36:37 -07:00
Daniel Han
1c063b4c98 Update _utils.py 2024-10-24 00:25:28 -07:00
Daniel Han
2b858a5b46 Merge branch 'main' into nightly 2024-10-24 00:24:27 -07:00
Daniel Han
4ff247ab18 Fix DPO, ORPO 2024-10-24 00:17:26 -07:00
Daniel Han
e561366365 Update cross_entropy_loss.py 2024-10-23 22:18:24 -07:00
Daniel Han
b821f20b36 n_items 2024-10-23 22:13:45 -07:00
Daniel Han
1e7e0e2368 Update _utils.py 2024-10-23 12:39:58 -07:00
Edd
f6a661f174
 		Fix/patch tokenizer (#1171) 
* fix: correct tokenizer handling in patch_sft_trainer_tokenizer

* Revert "fix: correct tokenizer handling in patch_sft_trainer_tokenizer"

This reverts commit f18ac214cd.

* fix: correct condition for test_text assignment in patch_sft_trainer_tokenizer
 2024-10-23 12:32:33 -07:00
Daniel Han
0e5a507f87
 		Many bug fixes (#1162) 
* Fix TRL

* Update mistral.py

* Patch processing_class

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Installation guide (#1165)

* chore: update chat_templates.py (#1166)

orginal -> original

* Disable Flex Attention

* Update tokenizer_utils.py

* Update _utils.py

---------

Co-authored-by: timothelaborie <97834767+timothelaborie@users.noreply.github.com>
Co-authored-by: Ikko Eltociear Ashimine <eltociear@gmail.com>
 2024-10-23 03:14:57 -07:00
Daniel Han
28e6eeabd8 Update _utils.py 2024-10-23 03:14:48 -07:00
Daniel Han
06f5d75b81 Update tokenizer_utils.py 2024-10-23 03:04:22 -07:00
Daniel Han
28958397ee Disable Flex Attention 2024-10-23 02:58:40 -07:00
Ikko Eltociear Ashimine
30bf33957d
 		chore: update chat_templates.py (#1166) 
orginal -> original
 2024-10-23 00:59:02 -07:00
timothelaborie
aabb5ff54b
 		Installation guide (#1165) 2024-10-23 00:55:26 -07:00
Daniel Han
b3e00335c1 Update tokenizer_utils.py 2024-10-22 01:28:38 -07:00
Daniel Han
c0f0fc987d Update tokenizer_utils.py 2024-10-22 01:22:13 -07:00
Daniel Han
101389d728 Update tokenizer_utils.py 2024-10-22 01:09:20 -07:00
Daniel Han
aa2b20763e Update tokenizer_utils.py 2024-10-22 01:05:41 -07:00
Daniel Han
4f7c527ae0 Update tokenizer_utils.py 2024-10-22 00:57:36 -07:00
Daniel Han
ef842120d2 Update tokenizer_utils.py 2024-10-22 00:55:47 -07:00
Daniel Han
106f213f40 Patch processing_class 2024-10-22 00:53:38 -07:00
Daniel Han
f4ae585405 Update mistral.py 2024-10-22 00:29:30 -07:00
Daniel Han
f0aca9073e Fix TRL 2024-10-21 01:02:53 -07:00
Daniel Han
1f52468fa3 Update save.py 2024-10-20 01:52:21 -07:00
Daniel Han
9327d90002 Update _utils.py 2024-10-18 23:10:30 -07:00
Daniel Han
d7850d8b2e Fix get_token 2024-10-18 23:08:30 -07:00
vo1d-ai
12bdd86636
 		fix: compute_loss bug (#1151) 
Currently, Unsloth doesn't pass additional parameters to Trainer.compute_loss such as return_outputs. This leads to errors when calling trainer.evaluate(). This change fixes the bug by properly passing parameters to Trainer.compute_loss.
 2024-10-18 20:46:07 -07:00
Daniel Han
3085f4c3da Update _utils.py 2024-10-17 20:50:05 -07:00
Daniel Han
b3e85e915e Update README.md 2024-10-17 20:46:11 -07:00
Daniel Han
eb533dbf14 Update README.md 2024-10-17 20:45:40 -07:00
Daniel Han
e210840ba9
 		Gradient Accumulation Fix (#1146) 
* Unsloth Zoo

* Update trainer.py

* Update trainer.py

* Update cross_entropy_loss.py

* n_items

* Update llama.py

* kwargs

* Remove extraneous f prefixes (#1133)

Co-authored-by: Emil Sadek <esadek@users.noreply.github.com>

* Update __init__.py

* kwargs

* Update trainer.py

* Update trainer.py

* Update trainer.py

* Fix GA

* Update _utils.py

* Update llama.py

* Update tokenizer_utils.py

* Warn on old versions

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

* Update tokenizer_utils.py

---------

Co-authored-by: Emil Sadek <esadek@hotmail.com>
Co-authored-by: Emil Sadek <esadek@users.noreply.github.com>
 2024-10-17 20:43:07 -07:00
Daniel Han
a395211e02 Update mapper.py 2024-10-16 21:48:05 -07:00
Daniel Han
38663b01f5
 		Gradient Accumulation Fix (#1134) 
* Unsloth Zoo

* Update trainer.py

* Update trainer.py

* Update cross_entropy_loss.py

* n_items

* Update llama.py

* kwargs

* Remove extraneous f prefixes (#1133)

Co-authored-by: Emil Sadek <esadek@users.noreply.github.com>

* Update __init__.py

---------

Co-authored-by: Emil Sadek <esadek@hotmail.com>
Co-authored-by: Emil Sadek <esadek@users.noreply.github.com>
 2024-10-14 19:17:35 -07:00
Daniel Han
a2f4c9793e Update save.py 2024-10-11 00:00:06 -07:00
Daniel Han
f397ad146b Update save.py 2024-10-10 23:22:17 -07:00
Giulia Baldini
13d434c208
 		Only remove folder in sentenpiece check if it was created (#1121) 2024-10-10 23:21:27 -07:00
Giulia Baldini
6d4fa754d9
 		Handle absolute paths using pathlib (#1120) 2024-10-10 23:20:34 -07:00
Daniel Han
79a2112ca4 Reload 2024-10-05 17:21:48 -07:00
Daniel Han
ae9e264e33 Merge branch 'nightly' 2024-10-01 00:45:16 -07:00
Daniel Han
39bff2f034 Update README.md 2024-10-01 00:40:17 -07:00
Daniel Han
2cab804e55 Update tokenizer_utils.py 2024-10-01 00:35:54 -07:00
Daniel Han
75d1006ad8 Update tokenizer_utils.py 2024-10-01 00:20:01 -07:00
Daniel Han
2efb9e151b Update tokenizer_utils.py 2024-10-01 00:14:52 -07:00