| _app | | | 143 items |
| _toctree.yml | 3.38 kB | | 9da8f3eb |
| async_grpo_trainer.html | 108 kB | | 4a8a4edc |
| async_grpo_trainer.md | 12.3 kB | | 4761da08 |
| bco_trainer.html | 130 kB | | 25f9080d |
| bco_trainer.md | 14.1 kB | | b53703d7 |
| bema_for_reference_model.html | 90 kB | | 20d227ca |
| bema_for_reference_model.md | 7.18 kB | | bf0f64f3 |
| callbacks.html | 95.8 kB | | 14ecc513 |
| callbacks.md | 7.88 kB | | b3031357 |
| chat_template_utils.html | 46.2 kB | | d9e5dcd2 |
| chat_template_utils.md | 5.76 kB | | df036e65 |
| chat_templates.html | 33.5 kB | | 3d745d2a |
| chat_templates.md | 6.03 kB | | 73fe5124 |
| clis.html | 53.4 kB | | 902a7bcc |
| clis.md | 12.8 kB | | 1961aea1 |
| community_tutorials.html | 31 kB | | a76cf59f |
| community_tutorials.md | 11 kB | | 60cc246e |
| cpo_trainer.html | 144 kB | | 73c92adc |
| cpo_trainer.md | 23 kB | | 64aa0892 |
| customization.html | 31 kB | | 3d678201 |
| customization.md | 4.08 kB | | bdc5c8a7 |
| data_utils.html | 62.7 kB | | 10725448 |
| data_utils.md | 6.87 kB | | 5b1abebc |
| dataset_formats.html | 223 kB | | d9d5b20a |
| dataset_formats.md | 40.2 kB | | 03119b52 |
| deepspeed_integration.html | 15.8 kB | | fb67aedf |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distillation_trainer.html | 161 kB | | 377753ac |
| distillation_trainer.md | 12.3 kB | | a7eba529 |
| distributing_training.html | 96.5 kB | | 0710e401 |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 233 kB | | 9e086fc8 |
| dpo_trainer.md | 30.8 kB | | 12f08661 |
| example_overview.html | 42.7 kB | | ed8b7235 |
| example_overview.md | 19.7 kB | | 49db3a9a |
| experimental_overview.html | 10.8 kB | | 830f6d01 |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 85 kB | | 70881e1b |
| gfpo.md | 5.24 kB | | 47923273 |
| gkd_trainer.html | 119 kB | | 8a2d3d90 |
| gkd_trainer.md | 14.1 kB | | c4520413 |
| gold_trainer.html | 166 kB | | b3f9e92d |
| gold_trainer.md | 18.1 kB | | be19560e |
| grpo_trainer.html | 561 kB | | 3e948731 |
| grpo_trainer.md | 55.8 kB | | adea421c |
| grpo_with_replay_buffer.html | 90.3 kB | | 238eb7b9 |
| grpo_with_replay_buffer.md | 6.16 kB | | 86d0924a |
| gspo_token.html | 50.2 kB | | 59550675 |
| gspo_token.md | 4.27 kB | | 75371f4c |
| index.html | 29 kB | | b2763c20 |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | d549e6a2 |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | 56b554eb |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| kernels_hub.html | 26.8 kB | | f0d5050d |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 138 kB | | 74fd161d |
| kto_trainer.md | 18.3 kB | | bc07e836 |
| liger_kernel_integration.html | 15 kB | | fb799119 |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 868 kB | | 2dcad452 |
| llms.txt | 5.15 kB | | 6961b260 |
| lora_without_regret.html | 45 kB | | 420c4d39 |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | 348ed3a7 |
| merge_model_callback.md | 1.19 kB | | 00ca0594 |
| minillm_trainer.html | 180 kB | | 5f02fc4f |
| minillm_trainer.md | 16.4 kB | | a0c032c8 |
| nash_md_trainer.html | 125 kB | | f2cff530 |
| nash_md_trainer.md | 16.3 kB | | a304c029 |
| nemo_gym.html | 58.5 kB | | 36ae5bf2 |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.45 kB | | f80bbe5b |
| online_dpo_trainer.html | 180 kB | | 6a61579a |
| online_dpo_trainer.md | 23.1 kB | | 3ad597e0 |
| openenv.html | 114 kB | | ae3b9978 |
| openenv.md | 27.8 kB | | 9ba775f9 |
| orpo_trainer.html | 127 kB | | 19142058 |
| orpo_trainer.md | 17.7 kB | | eba3fbc0 |
| paper_index.html | 742 kB | | 15b1eb28 |
| paper_index.md | 19.1 kB | | 61bd1ab5 |
| papo_trainer.html | 112 kB | | 594ec8e5 |
| papo_trainer.md | 8.82 kB | | d5a91980 |
| peft_integration.html | 131 kB | | c66dece0 |
| peft_integration.md | 23.9 kB | | 8200f157 |
| ppo_trainer.html | 279 kB | | e57c4845 |
| ppo_trainer.md | 41.4 kB | | e966a655 |
| prm_trainer.html | 118 kB | | 178446d2 |
| prm_trainer.md | 13.9 kB | | e45a4e6b |
| ptt_integration.html | 29.3 kB | | ec4c79a0 |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | 24f1089e |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 95.4 kB | | b0960232 |
| rapidfire_integration.md | 17.7 kB | | 08fed5af |
| reducing_memory_usage.html | 52.4 kB | | a43b1f9b |
| reducing_memory_usage.md | 12.3 kB | | d61af82e |
|