| _app | | | 228 items |
| _toctree.yml | 3.38 kB | | 9da8f3eb |
| async_grpo_trainer.html | 108 kB | | a576f3b7 |
| async_grpo_trainer.md | 12.3 kB | | e8e75147 |
| bco_trainer.html | 130 kB | | 68d511a9 |
| bco_trainer.md | 14.1 kB | | 1a6e578a |
| bema_for_reference_model.html | 90 kB | | ae8a656a |
| bema_for_reference_model.md | 7.18 kB | | 2eed7595 |
| callbacks.html | 95.8 kB | | 2a576fae |
| callbacks.md | 7.88 kB | | 191a2849 |
| chat_template_utils.html | 46.2 kB | | ab79f69f |
| chat_template_utils.md | 5.76 kB | | 72744fc3 |
| chat_templates.html | 33.5 kB | | f81a0e67 |
| chat_templates.md | 6.03 kB | | c3449daa |
| clis.html | 53.4 kB | | 853df2f8 |
| clis.md | 12.8 kB | | e81bee71 |
| community_tutorials.html | 31 kB | | c0f34413 |
| community_tutorials.md | 10.9 kB | | d90f90e7 |
| cpo_trainer.html | 144 kB | | 06e04905 |
| cpo_trainer.md | 23 kB | | 424e5c7e |
| customization.html | 30.9 kB | | 0ecbf207 |
| customization.md | 4.04 kB | | a465bf6a |
| data_utils.html | 62.7 kB | | f9685551 |
| data_utils.md | 6.87 kB | | 9c1a1b5b |
| dataset_formats.html | 223 kB | | eaef382d |
| dataset_formats.md | 40.1 kB | | 930e7de4 |
| deepspeed_integration.html | 15.8 kB | | 677c61a0 |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distillation_trainer.html | 161 kB | | b2d298df |
| distillation_trainer.md | 12.3 kB | | 51c97e47 |
| distributing_training.html | 96.5 kB | | bdb9b8d4 |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 232 kB | | 8b93d685 |
| dpo_trainer.md | 30.7 kB | | 4b3e0505 |
| example_overview.html | 42.7 kB | | 24cc5180 |
| example_overview.md | 19.6 kB | | 039782bf |
| experimental_overview.html | 10.8 kB | | 5ac62037 |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 85 kB | | 893f649f |
| gfpo.md | 5.24 kB | | 0e7f5592 |
| gkd_trainer.html | 119 kB | | abdfe63f |
| gkd_trainer.md | 14.1 kB | | 17a16013 |
| gold_trainer.html | 166 kB | | 3482b66f |
| gold_trainer.md | 18.1 kB | | 98d48857 |
| grpo_trainer.html | 561 kB | | 379f6e59 |
| grpo_trainer.md | 55.8 kB | | 7feda342 |
| grpo_with_replay_buffer.html | 90.3 kB | | 7df1d8ba |
| grpo_with_replay_buffer.md | 6.16 kB | | 5360d7ac |
| gspo_token.html | 50.2 kB | | c2185282 |
| gspo_token.md | 4.27 kB | | 3e359b70 |
| index.html | 29 kB | | 2c292167 |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | 206604fa |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | 8891c1af |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| kernels_hub.html | 26.8 kB | | 1e32df40 |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 138 kB | | 313a28b8 |
| kto_trainer.md | 18.3 kB | | 90c9076a |
| liger_kernel_integration.html | 15 kB | | 746c0a77 |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 867 kB | | 45b1a6a0 |
| llms.txt | 5.15 kB | | c1c7d593 |
| lora_without_regret.html | 45 kB | | 5876d8e7 |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | 1808670f |
| merge_model_callback.md | 1.19 kB | | b9b7defb |
| minillm_trainer.html | 180 kB | | 1bffe92f |
| minillm_trainer.md | 16.4 kB | | 2212994e |
| nash_md_trainer.html | 125 kB | | dba49f67 |
| nash_md_trainer.md | 16.3 kB | | bf209e0b |
| nemo_gym.html | 58.5 kB | | c66a0013 |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.44 kB | | 3a8d4fdd |
| online_dpo_trainer.html | 180 kB | | ecea754e |
| online_dpo_trainer.md | 23.1 kB | | d8f343fc |
| openenv.html | 114 kB | | 11665f30 |
| openenv.md | 27.8 kB | | f962036d |
| orpo_trainer.html | 127 kB | | a6f24c39 |
| orpo_trainer.md | 17.7 kB | | 86d4b107 |
| paper_index.html | 742 kB | | 70389132 |
| paper_index.md | 19.1 kB | | 33e86396 |
| papo_trainer.html | 112 kB | | 28f53f9a |
| papo_trainer.md | 8.82 kB | | 6c3a79db |
| peft_integration.html | 131 kB | | e7b8d19c |
| peft_integration.md | 23.9 kB | | 9340b87a |
| ppo_trainer.html | 279 kB | | 77ccd763 |
| ppo_trainer.md | 41.4 kB | | 26395f62 |
| prm_trainer.html | 118 kB | | ddb7acdc |
| prm_trainer.md | 13.9 kB | | fad3647c |
| ptt_integration.html | 29.3 kB | | 97c61b34 |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | 4097991a |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 95.4 kB | | 411d8349 |
| rapidfire_integration.md | 17.7 kB | | 08fed5af |
| reducing_memory_usage.html | 52.4 kB | | 0f2891d7 |
| reducing_memory_usage.md | 12.3 kB | | d61af82e |
|