|
|
9df19e8a75
|
📜 Fix license and copyrights (#3264)
|
2025-04-08 15:22:58 -07:00 |
|
|
|
b6bcafb8bb
|
🏃 Fix and make CI faster (#3160)
|
2025-04-08 06:12:08 -07:00 |
|
|
|
1d23ecc36f
|
©️ Update copyrights year (#2547)
* happy new year
* fix wandb import sort
|
2025-01-07 14:53:09 +01:00 |
|
|
|
9410874787
|
©️ Copyrights update (#2454)
* First changes
* Other files
* Finally
* rm comment
* fix nashmd
* Fix example
* Fix example [ci skip]
|
2024-12-10 10:40:00 +01:00 |
|
|
|
24fb32733f
|
🔧 Use standard unittest assertion methods (#2283)
* WIP: Partial unit test update
* Update unittest format
* Update tests/slow/test_sft_slow.py comment
* Refactor unit tests: replace pytest.raises with self.assertRaises
* Fix: Restore accidentally deleted 'ref_model' parameter in DPOTrainer
* Re-run pre-commit
* fix: Incorrectly replacing non-TestCase assert
---------
Co-authored-by: Quentin Gallouédec <45557362+qgallouedec@users.noreply.github.com>
|
2024-10-31 15:10:43 +01:00 |
|
|
|
10c2f63b2a
|
training_args for all TrainingArguments (#2082)
|
2024-09-19 15:03:47 +02:00 |
|
|
|
07f0e687cb
|
Use transformers utilities when possible (#2064)
* use transformers' availability functions
* require from transformers
* rm file
* fix no peft
* fix import
* don't alter _peft_available
* fix require_diffusers
* style
* transformers>=4.40 and add back `is_liger_kernel_available`
|
2024-09-16 15:56:49 +02:00 |
|
|
|
cbcaa46cd3
|
Various args and test fix (#1909)
* report to none
* simplify AlignPropTrainerTester
* rm unused marker
* Don't share setup in dpo trainer
* style
* don't share setup in test rich
* fix setup and classmethod
* fix args for sft
* test_trainer_args
* various arg fix
* report to none and vsdt simplifi
* drop generate_during_eval
* fix run_name
* style
* drop setUpClass
* style
* new ref values for ppo trainer tester
* update ref val
---------
Co-authored-by: Quentin Gallouédec <quentin.gallouedec@huggingface.co>
|
2024-08-09 10:07:58 +02:00 |
|
|
|
b5be100ae0
|
Added Reward Backpropogation Support (#1585)
* added alignprop template
* added alignprop support
* Update alignprop_trainer.mdx
* Update alignprop_trainer.mdx
* added better why statement
* fixed inference code
* changed self to pipeline
* removed aesthetic classifier
* added aesthetic to auxiliary models
* added unseen prompt logging
* removed unseen prompt log
* fixed minor
* remove not needed import in trl/__init__.py
Co-authored-by: Younes Belkada <49240599+younesbelkada@users.noreply.github.com>
* fixed styling
* updated _toctree
---------
Co-authored-by: Younes Belkada <49240599+younesbelkada@users.noreply.github.com>
|
2024-06-24 12:05:44 -04:00 |
|
