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

565 commits

This branch
This branch
All branches
Author SHA1 Message Date
Daniel Han
7555e3979c Merge branch 'main' into nightly 2024-10-24 00:24:27 -07:00
Daniel Han
cd1615dc64 Fix DPO, ORPO 2024-10-24 00:17:26 -07:00
Daniel Han
a048a791f4 Update cross_entropy_loss.py 2024-10-23 22:18:24 -07:00
Daniel Han
8390144201 n_items 2024-10-23 22:13:45 -07:00
Daniel Han
acef7d6a3d Update _utils.py 2024-10-23 12:39:58 -07:00
Edd
f402d945ff 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 7a98e465cbd4f980c8b364b0396d44f2d052090f.

* fix: correct condition for test_text assignment in patch_sft_trainer_tokenizer
 2024-10-23 12:32:33 -07:00
Daniel Han
e5e67f83b4 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
93cee86d9c Update _utils.py 2024-10-23 03:14:48 -07:00
Daniel Han
785a964f20 Update tokenizer_utils.py 2024-10-23 03:04:22 -07:00
Daniel Han
205b0437b3 Disable Flex Attention 2024-10-23 02:58:40 -07:00
Ikko Eltociear Ashimine
a8f79d46c6 chore: update chat_templates.py (#1166) 
orginal -> original
 2024-10-23 00:59:02 -07:00
timothelaborie
db0ce5d033 Installation guide (#1165) 2024-10-23 00:55:26 -07:00
Daniel Han
45b2689ad6 Update tokenizer_utils.py 2024-10-22 01:28:38 -07:00
Daniel Han
8f0a165a53 Update tokenizer_utils.py 2024-10-22 01:22:13 -07:00
Daniel Han
aaa151b15a Update tokenizer_utils.py 2024-10-22 01:09:20 -07:00
Daniel Han
11e63948e5 Update tokenizer_utils.py 2024-10-22 01:05:41 -07:00
Daniel Han
a952e13d6a Update tokenizer_utils.py 2024-10-22 00:57:36 -07:00
Daniel Han
010f24b3a7 Update tokenizer_utils.py 2024-10-22 00:55:47 -07:00
Daniel Han
e5e543c244 Patch processing_class 2024-10-22 00:53:38 -07:00
Daniel Han
d5becd080e Update mistral.py 2024-10-22 00:29:30 -07:00
Daniel Han
1ca9a03ab7 Fix TRL 2024-10-21 01:02:53 -07:00
Daniel Han
c3c9e1604b Update save.py 2024-10-20 01:52:21 -07:00
Daniel Han
251c3f9af2 Update _utils.py 2024-10-18 23:10:30 -07:00
Daniel Han
ac1c0fbaed Fix get_token 2024-10-18 23:08:30 -07:00
vo1d-ai
5dcc0cd613 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
94087e83d9 Update _utils.py 2024-10-17 20:50:05 -07:00
Daniel Han
f14e49d10f Update README.md 2024-10-17 20:46:11 -07:00
Daniel Han
a158a15965 Update README.md 2024-10-17 20:45:40 -07:00
Daniel Han
5e0a4bede8 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
98d68dae2b Update mapper.py 2024-10-16 21:48:05 -07:00
Daniel Han
c05e87f18d Gradient Accumulation Fix (#1134) October-2024 
* 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
f75a92d14d Update save.py 2024-10-11 00:00:06 -07:00
Daniel Han
71ac721cec Update save.py 2024-10-10 23:22:17 -07:00
Giulia Baldini
4ed744ef16 Only remove folder in sentenpiece check if it was created (#1121) 2024-10-10 23:21:27 -07:00
Giulia Baldini
3d00fbd7c7 Handle absolute paths using pathlib (#1120) 2024-10-10 23:20:34 -07:00
Daniel Han
8100844172 Reload 2024-10-05 17:21:48 -07:00
Daniel Han
bf6a87a608 Merge branch 'nightly' 2024-10-01 00:45:16 -07:00
Daniel Han
98a4a570ad Update README.md 2024-10-01 00:40:17 -07:00
Daniel Han
682f16aa5a Update tokenizer_utils.py 2024-10-01 00:35:54 -07:00
Daniel Han
cd530425f0 Update tokenizer_utils.py 2024-10-01 00:20:01 -07:00
Daniel Han
3ac34b5071 Update tokenizer_utils.py 2024-10-01 00:14:52 -07:00
Daniel Han
e1b0b8f6ef Update chat_templates.py 2024-09-30 23:08:46 -07:00
Daniel Han
ccfb9b68ff Fix merges (#1079) 
* Layernorm

* Update layernorm.py

* Update layernorm.py

* Update layernorm.py

* Update layernorm.py

* Update layernorm.py

* Update layernorm.py

* Patch layernorm

* Update layernorm.py

* RMS Layernorm

* Update rms_layernorm.py

* Causal LM

* Update cross_entropy_loss.py

* Update cross_entropy_loss.py

* Update cross_entropy_loss.py

* Update cross_entropy_loss.py

* Update layernorm.py

* Update cross_entropy_loss.py

* Update cross_entropy_loss.py

* Update cross_entropy_loss.py

* Update cross_entropy_loss.py

* Update cross_entropy_loss.py

* Update cross_entropy_loss.py

* Update cross_entropy_loss.py

* Update _utils.py

* Update _utils.py

* Llama 3.2

* Update _utils.py

* Update _utils.py

* Update _utils.py

* Update llama.py

* Update vision.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update llama.py

* Update loader.py

* Update loader.py

* Update loader.py

* Dependencies

* Update pyproject.toml

* Update _utils.py
 2024-09-30 03:03:01 -07:00
Daniel Han
cd7fe775fd Update _utils.py 2024-09-30 02:51:32 -07:00
Daniel Han
5147501121 Update pyproject.toml 2024-09-30 02:48:31 -07:00
Daniel Han
c8f45c8def Dependencies 2024-09-30 02:09:15 -07:00
Daniel Han
fa3b87e013 Update loader.py 2024-09-29 23:22:05 -07:00
Daniel Han
fe9171d15c Update loader.py 2024-09-29 23:15:22 -07:00
Daniel Han
98a1e16f57 Update loader.py 2024-09-29 23:13:44 -07:00
Daniel Han
679e2b601f Merge branch 'main' into nightly 2024-09-29 23:13:16 -07:00