| _app | | | 328 items |
| _toctree.yml | 3.43 kB | | 4aa162d5 |
| async_grpo_trainer.html | 108 kB | | c6c14cb5 |
| async_grpo_trainer.md | 12.3 kB | | 473a8391 |
| bco_trainer.html | 131 kB | | 19683bca |
| bco_trainer.md | 14.2 kB | | d7554e5e |
| bema_for_reference_model.html | 90 kB | | a270ccb4 |
| bema_for_reference_model.md | 7.18 kB | | 1e1068d7 |
| callbacks.html | 95.8 kB | | 810515fe |
| callbacks.md | 7.88 kB | | 03336a15 |
| chat_template_utils.html | 46.7 kB | | 39734f7c |
| chat_template_utils.md | 5.87 kB | | 8df614b6 |
| chat_templates.html | 44.7 kB | | 0cf0c780 |
| chat_templates.md | 8.74 kB | | 3ebdeb41 |
| clis.html | 53.6 kB | | 2841b6ac |
| clis.md | 12.8 kB | | 6b79a1ab |
| community_tutorials.html | 31 kB | | 11e11599 |
| community_tutorials.md | 11 kB | | a076202c |
| cpo_trainer.html | 145 kB | | 2840e672 |
| cpo_trainer.md | 23.2 kB | | ad8883c0 |
| customization.html | 31.1 kB | | 42a75c0a |
| customization.md | 4.08 kB | | 2da07ca9 |
| data_utils.html | 62.8 kB | | b1b1817a |
| data_utils.md | 6.87 kB | | 1625d167 |
| dataset_formats.html | 224 kB | | fdb8d414 |
| dataset_formats.md | 43 kB | | fd448fc4 |
| deepspeed_integration.html | 15.9 kB | | 8f8f0df5 |
| deepspeed_integration.md | 1.52 kB | | e5b0fad5 |
| distillation_trainer.html | 161 kB | | 3e4017eb |
| distillation_trainer.md | 12.3 kB | | 18d86fe4 |
| distributing_training.html | 96.7 kB | | f3485c1d |
| distributing_training.md | 21 kB | | 75949925 |
| dpo_trainer.html | 233 kB | | 29095cb5 |
| dpo_trainer.md | 31.1 kB | | 10b4cd17 |
| example_overview.html | 42.8 kB | | b4cf4876 |
| example_overview.md | 19.7 kB | | f0a8aaa5 |
| experimental_overview.html | 10.8 kB | | cdfdf435 |
| experimental_overview.md | 1.62 kB | | 45d90cc6 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 85.1 kB | | e4b0a16c |
| gfpo.md | 5.24 kB | | 3f6e210b |
| gkd_trainer.html | 119 kB | | c39f5e00 |
| gkd_trainer.md | 14.1 kB | | b992b3fa |
| gold_trainer.html | 166 kB | | b318798f |
| gold_trainer.md | 18.1 kB | | 726e6f8a |
| grpo_trainer.html | 562 kB | | 85b52144 |
| grpo_trainer.md | 61.5 kB | | d93cc2ff |
| grpo_with_replay_buffer.html | 90.3 kB | | babe947a |
| grpo_with_replay_buffer.md | 6.16 kB | | c1bf86ab |
| gspo_token.html | 50.2 kB | | bcc66175 |
| gspo_token.md | 4.27 kB | | dc8d027d |
| index.html | 29 kB | | 43b3af85 |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | 8b3a0947 |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 33.1 kB | | 70536847 |
| jobs_training.md | 6.46 kB | | cb814663 |
| kernels_hub.html | 26.9 kB | | 7c7baf1d |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 134 kB | | 1bea7dec |
| kto_trainer.md | 18.2 kB | | 39a9b155 |
| liger_kernel_integration.html | 15 kB | | d3ecaea9 |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 961 kB | | e3de11fd |
| llms.txt | 5.27 kB | | cba97cc8 |
| lora_without_regret.html | 45.1 kB | | 09b6145d |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | 9a1c03a0 |
| merge_model_callback.md | 1.19 kB | | 4258c075 |
| minillm_trainer.html | 180 kB | | 1d22102a |
| minillm_trainer.md | 16.4 kB | | 948b1eea |
| nash_md_trainer.html | 125 kB | | 9c3edecc |
| nash_md_trainer.md | 16.6 kB | | a66a8a00 |
| nemo_gym.html | 58.7 kB | | 7c079b30 |
| nemo_gym.md | 10.3 kB | | 45caccd9 |
| objects.inv | 2.47 kB | | 02ef30c4 |
| online_dpo_trainer.html | 180 kB | | 3ec31395 |
| online_dpo_trainer.md | 23.3 kB | | 0db2ed3b |
| openenv.html | 114 kB | | 16f626a8 |
| openenv.md | 27.8 kB | | 34442e1e |
| openreward.html | 67.4 kB | | 2d849086 |
| openreward.md | 10.6 kB | | 797cca7e |
| orpo_trainer.html | 128 kB | | 8176e406 |
| orpo_trainer.md | 17.9 kB | | 48e9e224 |
| paper_index.html | 763 kB | | 47d53b11 |
| paper_index.md | 85.1 kB | | 2a6173a8 |
| papo_trainer.html | 112 kB | | 18ef5d2a |
| papo_trainer.md | 8.82 kB | | e6559a5d |
| peft_integration.html | 131 kB | | 88668671 |
| peft_integration.md | 23.9 kB | | 433e0a21 |
| ppo_trainer.html | 279 kB | | c10e3ded |
| ppo_trainer.md | 41.5 kB | | 95bc0c93 |
| prm_trainer.html | 118 kB | | a4c6b499 |
| prm_trainer.md | 14.2 kB | | 5c0b1775 |
| ptt_integration.html | 29.3 kB | | 16ee0571 |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.5 kB | | 8ed954c1 |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 95.6 kB | | 374897c3 |
| rapidfire_integration.md | 17.8 kB | | b0dd6d2b |
|