| _app | | | 201 items |
| _toctree.yml | 3.38 kB | | 9da8f3eb |
| async_grpo_trainer.html | 108 kB | | 57778158 |
| async_grpo_trainer.md | 12.3 kB | | e5f60396 |
| bco_trainer.html | 130 kB | | 6a9c7c6b |
| bco_trainer.md | 14.1 kB | | 186b5fe1 |
| bema_for_reference_model.html | 90 kB | | 0fc00d45 |
| bema_for_reference_model.md | 7.18 kB | | fbfcdb3f |
| callbacks.html | 95.8 kB | | 97de782d |
| callbacks.md | 7.88 kB | | 070627e8 |
| chat_template_utils.html | 45.9 kB | | 3a4bd64e |
| chat_template_utils.md | 5.52 kB | | 7dc473d1 |
| chat_templates.html | 33.5 kB | | 7574c029 |
| chat_templates.md | 6.03 kB | | 34d331d1 |
| clis.html | 53.4 kB | | 0f13f9ec |
| clis.md | 12.8 kB | | 37537f1a |
| community_tutorials.html | 31 kB | | 047c8e7a |
| community_tutorials.md | 10.9 kB | | e7d1a8ca |
| cpo_trainer.html | 144 kB | | 10ffcdfd |
| cpo_trainer.md | 23 kB | | 522c1a2e |
| customization.html | 30.9 kB | | 95fbbc11 |
| customization.md | 4.04 kB | | ea892614 |
| data_utils.html | 62.7 kB | | 15274a69 |
| data_utils.md | 6.87 kB | | cb2619b1 |
| dataset_formats.html | 223 kB | | b4b5eb5c |
| dataset_formats.md | 40.1 kB | | 4e4b0b7c |
| deepspeed_integration.html | 15.8 kB | | 7acef550 |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distillation_trainer.html | 161 kB | | a030c221 |
| distillation_trainer.md | 12.3 kB | | 75220d44 |
| distributing_training.html | 96.5 kB | | 7430be9f |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 232 kB | | cc709150 |
| dpo_trainer.md | 30.7 kB | | c23661a0 |
| example_overview.html | 42.7 kB | | c6c814f9 |
| example_overview.md | 19.6 kB | | ca7a3665 |
| experimental_overview.html | 10.8 kB | | e5baa5be |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 85 kB | | c22b4719 |
| gfpo.md | 5.24 kB | | e468bf40 |
| gkd_trainer.html | 119 kB | | 04f3054e |
| gkd_trainer.md | 14.1 kB | | 61b24a68 |
| gold_trainer.html | 166 kB | | ee345b1f |
| gold_trainer.md | 18.1 kB | | cc0d0c05 |
| grpo_trainer.html | 561 kB | | c5881bc2 |
| grpo_trainer.md | 55.8 kB | | 883af31f |
| grpo_with_replay_buffer.html | 90.3 kB | | 22805911 |
| grpo_with_replay_buffer.md | 6.16 kB | | 919207d3 |
| gspo_token.html | 50.2 kB | | 0ab49641 |
| gspo_token.md | 4.27 kB | | 024c1ff9 |
| index.html | 29 kB | | bdf74dbc |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | d8704567 |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | a2b70810 |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| kernels_hub.html | 26.8 kB | | 3699191c |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 138 kB | | c3d342a5 |
| kto_trainer.md | 18.3 kB | | c5742fef |
| liger_kernel_integration.html | 15 kB | | 8d3600ab |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 867 kB | | ce2c5e87 |
| llms.txt | 5.15 kB | | d6ab9909 |
| lora_without_regret.html | 45 kB | | f72f58f7 |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | fd695c02 |
| merge_model_callback.md | 1.19 kB | | 8e2679d0 |
| minillm_trainer.html | 180 kB | | 6f08cd1d |
| minillm_trainer.md | 16.4 kB | | 18f756d1 |
| nash_md_trainer.html | 125 kB | | 99421225 |
| nash_md_trainer.md | 16.3 kB | | 00c18110 |
| nemo_gym.html | 58.5 kB | | 1ab2a444 |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.44 kB | | 546e463a |
| online_dpo_trainer.html | 180 kB | | cdfd8e2f |
| online_dpo_trainer.md | 23.1 kB | | 12a2cb6d |
| openenv.html | 114 kB | | 508e368f |
| openenv.md | 27.8 kB | | 52dc93d4 |
| orpo_trainer.html | 127 kB | | 0f8ba796 |
| orpo_trainer.md | 17.7 kB | | e4d93aa3 |
| paper_index.html | 742 kB | | 25b0f5b1 |
| paper_index.md | 19.1 kB | | 2dc7c0eb |
| papo_trainer.html | 112 kB | | fce97505 |
| papo_trainer.md | 8.82 kB | | f6a7ddce |
| peft_integration.html | 131 kB | | 593d64a1 |
| peft_integration.md | 23.9 kB | | 6af16a34 |
| ppo_trainer.html | 279 kB | | 57c3756a |
| ppo_trainer.md | 41.4 kB | | daea2109 |
| prm_trainer.html | 118 kB | | 13a0492c |
| prm_trainer.md | 13.9 kB | | 93af2d41 |
| ptt_integration.html | 29.3 kB | | a15eacfa |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | 89a2fb1b |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 95.4 kB | | 78fca061 |
| rapidfire_integration.md | 17.7 kB | | 08fed5af |
| reducing_memory_usage.html | 52.4 kB | | 04fb6d0c |
| reducing_memory_usage.md | 12.3 kB | | d61af82e |
|