Commit graph

541 commits

Author SHA1 Message Date
vo1d-ai
f63a2a5026 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
cde7401259 Update _utils.py 2024-10-17 20:50:05 -07:00
Daniel Han
139c3b29b3 Update README.md 2024-10-17 20:46:11 -07:00
Daniel Han
3a33dad3c9 Update README.md 2024-10-17 20:45:40 -07:00
Daniel Han
d57dcf58a1 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
6ba202708c Update mapper.py 2024-10-16 21:48:05 -07:00
Daniel Han
d2a032e117 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
5bd7d3640f Update save.py 2024-10-11 00:00:06 -07:00
Daniel Han
9dd4462bf9 Update save.py 2024-10-10 23:22:17 -07:00
Giulia Baldini
592191b061 Only remove folder in sentenpiece check if it was created (#1121) 2024-10-10 23:21:27 -07:00
Giulia Baldini
5f2d5a3021 Handle absolute paths using pathlib (#1120) 2024-10-10 23:20:34 -07:00
Daniel Han
e130e748f0 Reload 2024-10-05 17:21:48 -07:00
Daniel Han
c89ae6b9b4 Merge branch 'nightly' 2024-10-01 00:45:16 -07:00
Daniel Han
3c47723bb2 Update README.md 2024-10-01 00:40:17 -07:00
Daniel Han
7fc9b07b94 Update tokenizer_utils.py 2024-10-01 00:35:54 -07:00
Daniel Han
3017eae097 Update tokenizer_utils.py 2024-10-01 00:20:01 -07:00
Daniel Han
dfc5cd3c80 Update tokenizer_utils.py 2024-10-01 00:14:52 -07:00
Daniel Han
ac3f564f7e Update chat_templates.py 2024-09-30 23:08:46 -07:00
Daniel Han
248c27d205 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
0f1f2cf728 Update _utils.py 2024-09-30 02:51:32 -07:00
Daniel Han
906f88bb4d Update pyproject.toml 2024-09-30 02:48:31 -07:00
Daniel Han
e31152134e Dependencies 2024-09-30 02:09:15 -07:00
Daniel Han
45916d36cf Update loader.py 2024-09-29 23:22:05 -07:00
Daniel Han
a529a39c81 Update loader.py 2024-09-29 23:15:22 -07:00
Daniel Han
f744b3159e Update loader.py 2024-09-29 23:13:44 -07:00
Daniel Han
ab43e02a94 Merge branch 'main' into nightly 2024-09-29 23:13:16 -07:00
Daniel Han
afbb140a79 Update loader.py 2024-09-29 01:42:58 -07:00
Daniel Han
b314837622 Update pyproject.toml 2024-09-27 01:36:45 -07:00
Daniel Han
c0b4d640f2 Update tokenizer_utils.py 2024-09-26 01:23:40 -07:00
Daniel Han
88a542a129 Update README.md 2024-09-26 00:12:42 -07:00
Daniel Han
6bbca3aaa8 Update README.md 2024-09-26 00:05:38 -07:00
Daniel Han
4f4ef22035 Update README.md 2024-09-26 00:02:15 -07:00
Daniel Han
930d2ad1a8 Update pyproject.toml 2024-09-25 23:47:15 -07:00
Daniel Han
5b345ec757 Update pyproject.toml 2024-09-25 23:13:49 -07:00
Daniel Han
c331c886ee Remove version checks 2024-09-25 23:00:09 -07:00
Daniel Han
63e3a85efb Update _utils.py 2024-09-25 22:56:41 -07:00
Daniel Han
dc8bca6713 Update llama.py 2024-09-25 22:12:21 -07:00
Daniel Han
8c6acbc6ce Update llama.py 2024-09-25 19:38:01 -07:00
Daniel Han
50b9003936 Update llama.py 2024-09-25 19:15:40 -07:00
Daniel Han
70775fa740 Update llama.py 2024-09-25 18:24:30 -07:00
Daniel Han
013a2ed95b Update llama.py 2024-09-25 18:10:46 -07:00
Daniel Han
8d910ecba9 Update llama.py 2024-09-25 18:07:21 -07:00
Daniel Han
ff921b8601 Update llama.py 2024-09-25 17:55:42 -07:00
Daniel Han
b61d75592a Update llama.py 2024-09-25 17:51:36 -07:00
Daniel Han
2aae911368 Update llama.py 2024-09-25 17:46:29 -07:00
Daniel Han
48777c492a Update vision.py 2024-09-25 17:44:13 -07:00
Daniel Han
62791d8f98 Update llama.py 2024-09-25 14:32:29 -07:00
Daniel Han
2af2e6e439 Update _utils.py 2024-09-25 14:12:16 -07:00
Daniel Han
54e59f3f49 Update _utils.py 2024-09-25 13:28:05 -07:00
Daniel Han
4e516b76c5 Update _utils.py 2024-09-25 13:19:01 -07:00