| _app | | | 141 items |
| _toctree.yml | 3.57 kB | | 60cb764b |
| a2po_trainer.html | 103 kB | | 4713ea6f |
| a2po_trainer.md | 8.32 kB | | d2521047 |
| async_grpo_trainer.html | 145 kB | | 4bf17fcc |
| async_grpo_trainer.md | 17.1 kB | | 0f16bab8 |
| bco_trainer.html | 135 kB | | 9f93a397 |
| bco_trainer.md | 15.1 kB | | 07e7d161 |
| bema_for_reference_model.html | 90.1 kB | | 571765ec |
| bema_for_reference_model.md | 7.19 kB | | 50124d9f |
| callbacks.html | 96 kB | | 0e1b6d4b |
| callbacks.md | 7.9 kB | | 9523c6eb |
| chat_template_utils.html | 47 kB | | b251a82b |
| chat_template_utils.md | 5.95 kB | | ac53372b |
| chat_templates.html | 61.7 kB | | 10c50b5e |
| chat_templates.md | 12.5 kB | | e79ac998 |
| clis.html | 53.6 kB | | 931c148f |
| clis.md | 12.8 kB | | 652ac792 |
| community_tutorials.html | 31.1 kB | | 67a44101 |
| community_tutorials.md | 11 kB | | 1811d5b2 |
| cpo_trainer.html | 146 kB | | 466c9eb5 |
| cpo_trainer.md | 23.5 kB | | fba7a856 |
| customization.html | 31.1 kB | | 2fad54f4 |
| customization.md | 4.08 kB | | 1773d736 |
| data_utils.html | 63 kB | | 26f12a50 |
| data_utils.md | 7.01 kB | | 0046906d |
| dataset_formats.html | 224 kB | | 91b1a811 |
| dataset_formats.md | 43 kB | | 949f52a4 |
| deepspeed_integration.html | 15.9 kB | | b469e254 |
| deepspeed_integration.md | 1.52 kB | | e5b0fad5 |
| distillation_trainer.html | 164 kB | | 37e5ca0f |
| distillation_trainer.md | 12.3 kB | | 7d295df2 |
| distributing_training.html | 96.7 kB | | e1d70da2 |
| distributing_training.md | 21 kB | | 2b14cde4 |
| dpo_trainer.html | 235 kB | | 26068dd3 |
| dpo_trainer.md | 31.1 kB | | 813a1177 |
| example_overview.html | 46.3 kB | | defcbb3c |
| example_overview.md | 22.5 kB | | 1e756abb |
| experimental_overview.html | 10.8 kB | | 7e86417c |
| experimental_overview.md | 1.62 kB | | 45d90cc6 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 86.6 kB | | 189aa073 |
| gfpo.md | 5.24 kB | | 67482075 |
| gkd_trainer.html | 120 kB | | 30ebdc2c |
| gkd_trainer.md | 14.1 kB | | 52946a31 |
| gmpo.html | 89 kB | | 992957b1 |
| gmpo.md | 6.75 kB | | 4ece1301 |
| gold_trainer.html | 186 kB | | c5bb786c |
| gold_trainer.md | 12.9 kB | | 5adba2b2 |
| grpo_trainer.html | 588 kB | | 194307eb |
| grpo_trainer.md | 65.1 kB | | 9b9ec52a |
| grpo_with_replay_buffer.html | 91.8 kB | | dd1bd439 |
| grpo_with_replay_buffer.md | 6.16 kB | | f0237082 |
| gspo_token.html | 50.2 kB | | f6d59c50 |
| gspo_token.md | 4.27 kB | | 2ea09b0d |
| harbor.html | 77.6 kB | | bf9b76b2 |
| harbor.md | 13.5 kB | | da1ee9ee |
| index.html | 29.3 kB | | d3ece862 |
| index.md | 3.9 kB | | 2bd5daf8 |
| installation.html | 13.9 kB | | 410daf89 |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 33.1 kB | | 65f20312 |
| jobs_training.md | 6.45 kB | | 38e66142 |
| kernels_hub.html | 26.9 kB | | 42e6b4fc |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 151 kB | | a9b08340 |
| kto_trainer.md | 21 kB | | 0fe677df |
| liger_kernel_integration.html | 15 kB | | 2c244980 |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 1.02 MB | | ce6ef25c |
| llms.txt | 5.51 kB | | 358d86c1 |
| lora_without_regret.html | 45.1 kB | | f32a55c5 |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 18 kB | | 9dd27db0 |
| merge_model_callback.md | 1.21 kB | | 4453c808 |
| minillm_trainer.html | 182 kB | | 6c2c8e34 |
| minillm_trainer.md | 16.5 kB | | fad7577a |
| nash_md_trainer.html | 126 kB | | 92015e3f |
| nash_md_trainer.md | 16.6 kB | | 68e0713f |
| objects.inv | 2.69 kB | | 11743adb |
| online_dpo_trainer.html | 183 kB | | f9de4025 |
| online_dpo_trainer.md | 23.3 kB | | e425b5a3 |
| openenv.html | 116 kB | | cada880a |
| openenv.md | 28.2 kB | | 0d991cae |
| openreward.html | 71.5 kB | | 1659cb74 |
| openreward.md | 11.5 kB | | 7e945aae |
| orpo_trainer.html | 129 kB | | f35d1633 |
| orpo_trainer.md | 18.2 kB | | 4d8d2468 |
| paper_index.html | 813 kB | | e192a33f |
| paper_index.md | 90 kB | | 2da147fb |
| papo_trainer.html | 114 kB | | 57fff4ab |
| papo_trainer.md | 8.91 kB | | 32328097 |
| peft_integration.html | 131 kB | | 35304f8e |
| peft_integration.md | 23.9 kB | | ad1b767e |
| ppo_trainer.html | 280 kB | | 95792c99 |
| ppo_trainer.md | 42.3 kB | | bbf14691 |
| prm_trainer.html | 118 kB | | 1883f9dc |
| prm_trainer.md | 14.2 kB | | 431807d6 |
| ptt_integration.html | 29.3 kB | | 56338588 |
| ptt_integration.md | 4.27 kB | | 6a21357a |
|