| _app | | | 215 items |
| _toctree.yml | 3.31 kB | | 222c63dd |
| a2po_trainer.html | 102 kB | | a160a8f3 |
| a2po_trainer.md | 16.7 kB | | 29f33dd7 |
| async_distillation_trainer.html | 173 kB | | 16f7b726 |
| async_distillation_trainer.md | 53.2 kB | | 15e50ebf |
| async_grpo_trainer.html | 215 kB | | d0eb0e3d |
| async_grpo_trainer.md | 65 kB | | 12eae3e7 |
| bema_for_reference_model.html | 91.5 kB | | 7897db04 |
| bema_for_reference_model.md | 7.12 kB | | e0d56d9f |
| callbacks.html | 97.5 kB | | ab3b7cf9 |
| callbacks.md | 8.91 kB | | 231a784c |
| chat_template_utils.html | 46 kB | | dcbdfc53 |
| chat_template_utils.md | 7.1 kB | | 3bcc935c |
| chat_templates.html | 72.1 kB | | 11aed1a3 |
| chat_templates.md | 15.4 kB | | 426ade8f |
| clis.html | 53.9 kB | | da7af452 |
| clis.md | 12.9 kB | | 0ed2f672 |
| community_tutorials.html | 30.8 kB | | 79c2564a |
| community_tutorials.md | 11 kB | | 188c91e8 |
| cpo_trainer.html | 141 kB | | 8d5e4087 |
| cpo_trainer.md | 29.1 kB | | ac9dc428 |
| customization.html | 45.5 kB | | 0a1dd81c |
| customization.md | 7.5 kB | | 6e966dac |
| data_utils.html | 59.8 kB | | e4d8b579 |
| data_utils.md | 7.28 kB | | 8d445905 |
| dataset_formats.html | 190 kB | | 45f04573 |
| dataset_formats.md | 36.8 kB | | 4b314259 |
| deepspeed_integration.html | 15.4 kB | | b946053b |
| deepspeed_integration.md | 1.46 kB | | 0c0b6c40 |
| distillation_trainer.html | 232 kB | | e7b2f7fc |
| distillation_trainer.md | 40.3 kB | | 27ed14ae |
| distributing_training.html | 32.6 kB | | 4692d166 |
| distributing_training.md | 4.93 kB | | 2834266a |
| dpo_trainer.html | 238 kB | | 954f173f |
| dpo_trainer.md | 46.9 kB | | 751b17f1 |
| example_overview.html | 32.4 kB | | f792e593 |
| example_overview.md | 15.8 kB | | 5f2d3825 |
| experimental_overview.html | 13.4 kB | | 9dd8f75f |
| experimental_overview.md | 3.04 kB | | 43e69c0b |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gkd_trainer.html | 118 kB | | 4d2858f9 |
| gkd_trainer.md | 20.9 kB | | 1be6cce4 |
| gmpo.html | 89.2 kB | | c602ff3d |
| gmpo.md | 13.7 kB | | b4fb0f37 |
| gold_trainer.html | 192 kB | | 771fc3e8 |
| gold_trainer.md | 33.3 kB | | 5da28c0a |
| grpo_trainer.html | 634 kB | | 2bcd97cd |
| grpo_trainer.md | 114 kB | | 7ab5c43e |
| harbor.html | 76.4 kB | | 6d2cfb95 |
| harbor.md | 13.8 kB | | 8d781969 |
| index.html | 36.6 kB | | 43caeb61 |
| index.md | 4.57 kB | | f45595a7 |
| installation.html | 13.7 kB | | 900db346 |
| installation.md | 721 Bytes | | 93a212e0 |
| iw_opd_trainer.html | 143 kB | | a321778b |
| iw_opd_trainer.md | 21.4 kB | | 3d5462fe |
| jobs_training.html | 58.7 kB | | d3f014a0 |
| jobs_training.md | 17.4 kB | | 12938320 |
| kernels_hub.html | 30.8 kB | | 845784fd |
| kernels_hub.md | 5.67 kB | | 9dc552d3 |
| kto_trainer.html | 220 kB | | eea8292f |
| kto_trainer.md | 42.5 kB | | 3c274ac5 |
| liger_kernel_integration.html | 15.6 kB | | 7ac8314b |
| liger_kernel_integration.md | 2.82 kB | | 84528c41 |
| llms-full.txt | 1.31 MB | | 7b13470b |
| llms.txt | 5.01 kB | | 25bdca44 |
| long_context_training.html | 50.5 kB | | 0172d515 |
| long_context_training.md | 13.2 kB | | 1d021950 |
| lora_without_regret.html | 44.1 kB | | 8ce886aa |
| lora_without_regret.md | 14.3 kB | | e31f56a0 |
| merge_model_callback.html | 17.6 kB | | d4da4acb |
| merge_model_callback.md | 1.39 kB | | d5e10a4a |
| minillm_trainer.html | 181 kB | | f0ecf91c |
| minillm_trainer.md | 25.5 kB | | 602caa5d |
| objects.inv | 2.22 kB | | e6b2d106 |
| online_dpo_trainer.html | 177 kB | | 158eb846 |
| online_dpo_trainer.md | 35.9 kB | | 4d71186e |
| openenv.html | 131 kB | | 1c45a6d3 |
| openenv.md | 35.1 kB | | 2756c03c |
| openreward.html | 70.4 kB | | fb3be2de |
| openreward.md | 11.9 kB | | 8f07de88 |
| orpo_trainer.html | 124 kB | | 299e5fe4 |
| orpo_trainer.md | 23.7 kB | | f85612c4 |
| paper_index.html | 822 kB | | 2a69f181 |
| paper_index.md | 92.5 kB | | 903c3812 |
| peft_integration.html | 119 kB | | 6b3b196c |
| peft_integration.md | 21.9 kB | | 8d4baad8 |
| quickstart.html | 37.6 kB | | b8c77a45 |
| quickstart.md | 3.62 kB | | d6c66824 |
| rapidfire_integration.html | 94.2 kB | | 4bc2f89e |
| rapidfire_integration.md | 17.8 kB | | 337b5dbc |
| reducing_memory_usage.html | 63 kB | | d1580a96 |
| reducing_memory_usage.md | 14.9 kB | | 5386b50c |
| reward_trainer.html | 179 kB | | e89e78db |
| reward_trainer.md | 31.6 kB | | 2fb94e15 |
| rewards.html | 123 kB | | 10d3350b |
| rewards.md | 12.4 kB | | d06d41b5 |
| rloo_trainer.html | 412 kB | | dd2a72e6 |
| rloo_trainer.md | 68.8 kB | | 1617d7c7 |
|