| _app | | | 155 items |
| _toctree.yml | 3.15 kB | | 23c10302 |
| bco_trainer.html | 142 kB | | c784181d |
| bco_trainer.md | 14.3 kB | | 50093f64 |
| bema_for_reference_model.html | 91.3 kB | | 0b472866 |
| bema_for_reference_model.md | 7.7 kB | | c88e0917 |
| callbacks.html | 101 kB | | c2d3da72 |
| callbacks.md | 8.14 kB | | bd05a4db |
| chat_template_utils.html | 69.6 kB | | c114f3e5 |
| chat_template_utils.md | 7.34 kB | | 1e6454a7 |
| clis.html | 53.4 kB | | d92ccaf9 |
| clis.md | 12.8 kB | | cfbd342a |
| community_tutorials.html | 30.3 kB | | ee18a28d |
| community_tutorials.md | 10.4 kB | | d8b57f95 |
| cpo_trainer.html | 154 kB | | 68fdc82e |
| cpo_trainer.md | 22.9 kB | | dcf93ca0 |
| customization.html | 37.4 kB | | bbf4bbce |
| customization.md | 4.9 kB | | f14afb2a |
| data_utils.html | 177 kB | | de42e81b |
| data_utils.md | 18.9 kB | | 07ae3685 |
| dataset_formats.html | 219 kB | | de8af8f4 |
| dataset_formats.md | 41.2 kB | | a9ddd847 |
| deepspeed_integration.html | 15.9 kB | | e717c677 |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distributing_training.html | 80.9 kB | | c0b071a3 |
| distributing_training.md | 18.8 kB | | 3b39fd9e |
| dpo_trainer.html | 251 kB | | c03f5f04 |
| dpo_trainer.md | 35.4 kB | | 88f78ebb |
| example_overview.html | 34.6 kB | | ae4d4b4c |
| example_overview.md | 15.4 kB | | 06e3979e |
| experimental_overview.html | 10.8 kB | | 673d4b98 |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 89 kB | | ac74b924 |
| gfpo.md | 5.35 kB | | 262ff5db |
| gkd_trainer.html | 123 kB | | aa6b7303 |
| gkd_trainer.md | 13.9 kB | | 7d0ce45d |
| gold_trainer.html | 144 kB | | 1f689ec4 |
| gold_trainer.md | 13.8 kB | | ab7e8bd7 |
| grpo_trainer.html | 527 kB | | f45ea324 |
| grpo_trainer.md | 47.2 kB | | ddfc9391 |
| grpo_with_replay_buffer.html | 94.3 kB | | d0bd6a76 |
| grpo_with_replay_buffer.md | 6.27 kB | | 75ac7b8a |
| gspo_token.html | 50.6 kB | | 8b71beea |
| gspo_token.md | 4.38 kB | | 71febb9d |
| index.html | 28.6 kB | | a33a6254 |
| index.md | 3.68 kB | | a08ded5f |
| installation.html | 13.9 kB | | 3cda5dff |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | af0b24b6 |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| judges.html | 119 kB | | 4babdf01 |
| judges.md | 15 kB | | fbc73fdf |
| kernels_hub.html | 26.8 kB | | 66ff0adc |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 159 kB | | 7e0c0a9e |
| kto_trainer.md | 20.7 kB | | 49104c17 |
| liger_kernel_integration.html | 15 kB | | 3f3d3013 |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 810 kB | | 92d3d911 |
| llms.txt | 4.76 kB | | 1246c89a |
| lora_without_regret.html | 45.1 kB | | b77c93fc |
| lora_without_regret.md | 14.5 kB | | 38851bd7 |
| merge_model_callback.html | 17.8 kB | | 8d051642 |
| merge_model_callback.md | 1.19 kB | | f2a8c1d2 |
| minillm_trainer.html | 184 kB | | fb1cbb73 |
| minillm_trainer.md | 16.5 kB | | 2b65085a |
| model_utils.html | 40.7 kB | | 30abc671 |
| model_utils.md | 3.42 kB | | d3141646 |
| nash_md_trainer.html | 134 kB | | d6ef9fe3 |
| nash_md_trainer.md | 16.7 kB | | d1ef7661 |
| objects.inv | 2.56 kB | | 708eb6a2 |
| online_dpo_trainer.html | 195 kB | | 543c815d |
| online_dpo_trainer.md | 25.5 kB | | ece76f5f |
| openenv.html | 86.4 kB | | 96b4168f |
| openenv.md | 24.9 kB | | 1ece954d |
| orpo_trainer.html | 136 kB | | fe68d51e |
| orpo_trainer.md | 17.6 kB | | b0426454 |
| others.html | 27.7 kB | | 8c4d73fb |
| others.md | 1.83 kB | | 05b56c56 |
| paper_index.html | 401 kB | | bee2be4b |
| paper_index.md | 26.2 kB | | b1cb7c16 |
| papo_trainer.html | 116 kB | | 98a5e477 |
| papo_trainer.md | 8.83 kB | | 754fc0c7 |
| peft_integration.html | 131 kB | | 2731a7ed |
| peft_integration.md | 23.8 kB | | 575f6bb6 |
| ppo_trainer.html | 284 kB | | 5163a510 |
| ppo_trainer.md | 41.3 kB | | beec07b1 |
| prm_trainer.html | 123 kB | | 9a42bec7 |
| prm_trainer.md | 13.7 kB | | ddf70ad3 |
| quickstart.html | 37.7 kB | | e1b8c118 |
| quickstart.md | 3.36 kB | | 1a8bc789 |
| rapidfire_integration.html | 81.2 kB | | 13654484 |
| rapidfire_integration.md | 12.8 kB | | 33fdfe4a |
| reducing_memory_usage.html | 52.7 kB | | 58bfbe42 |
| reducing_memory_usage.md | 11.7 kB | | ff163a93 |
| reward_trainer.html | 198 kB | | 733a15d2 |
| reward_trainer.md | 23.4 kB | | b75a1e2d |
| rewards.html | 75.8 kB | | cdd36695 |
| rewards.md | 6.31 kB | | 27dfe5f1 |
|