| _app | | | 96 items |
| _toctree.yml | 2.57 kB | | 6b5537fb |
| alignprop_trainer.html | 25 kB | | 69399340 |
| bco_trainer.html | 178 kB | | b867df73 |
| best_of_n.html | 15.7 kB | | 188c194f |
| callbacks.html | 57.1 kB | | e00d8144 |
| clis.html | 66.1 kB | | 17a55a9f |
| community_tutorials.html | 14.4 kB | | e6c2b70f |
| cpo_trainer.html | 189 kB | | 90f3cee9 |
| customization.html | 35.9 kB | | 0a0460a5 |
| data_utils.html | 89.9 kB | | 4b4923f4 |
| dataset_formats.html | 204 kB | | 3774d412 |
| ddpo_trainer.html | 144 kB | | 0548d723 |
| deepspeed_integration.html | 4.15 kB | | 334fef24 |
| detoxifying_a_lm.html | 46.3 kB | | 5dbd3c26 |
| dpo_trainer.html | 280 kB | | 7e717718 |
| example_overview.html | 23.5 kB | | 458285a7 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gkd_trainer.html | 92.1 kB | | f7406391 |
| how_to_train.html | 20.7 kB | | bcaecd28 |
| index.html | 14.6 kB | | c274b717 |
| installation.html | 10.6 kB | | 89321ea0 |
| iterative_sft_trainer.html | 57.2 kB | | f012964c |
| judges.html | 117 kB | | 33927c3d |
| kto_trainer.html | 193 kB | | 6f7d167c |
| learning_tools.html | 44.9 kB | | 7a3ea570 |
| liger_kernel_integration.html | 4.17 kB | | f0d3ff4f |
| logging.html | 16.5 kB | | 8f3d34a0 |
| models.html | 124 kB | | f51400e0 |
| multi_adapter_rl.html | 21.9 kB | | 621848d8 |
| nash_md_trainer.html | 101 kB | | ae54c4fb |
| objects.inv | 2.28 kB | | 5b8e40da |
| online_dpo_trainer.html | 141 kB | | efad3f63 |
| orpo_trainer.html | 177 kB | | 9d27e6d1 |
| peft_integration.html | 35.8 kB | | 34e48b13 |
| ppo_trainer.html | 118 kB | | 14fe4b92 |
| prm_trainer.html | 124 kB | | 91778145 |
| quickstart.html | 17.3 kB | | e8478ec1 |
| reducing_memory_usage.html | 13.8 kB | | 47f8d564 |
| reward_trainer.html | 86.3 kB | | 9d3dcd0b |
| rloo_trainer.html | 111 kB | | dff0f468 |
| script_utils.html | 55.9 kB | | 2daa6047 |
| sentiment_tuning.html | 11.1 kB | | 3353e793 |
| sft_trainer.html | 287 kB | | 15b80395 |
| speeding_up_training.html | 4.14 kB | | 4d816008 |
| text_environments.html | 104 kB | | 3053fc17 |
| unsloth_integration.html | 4.13 kB | | 9ab4e954 |
| use_model.html | 15.1 kB | | fff9c0fe |
| using_llama_models.html | 30.6 kB | | bbd8950d |
| xpo_trainer.html | 101 kB | | 1a182f37 |