| _app | | | 158 items |
| _toctree.yml | 3.38 kB | | 9da8f3eb |
| async_grpo_trainer.html | 108 kB | | 044c011d |
| async_grpo_trainer.md | 12.3 kB | | 78c3f49a |
| bco_trainer.html | 130 kB | | a94cae88 |
| bco_trainer.md | 14.2 kB | | 942eda3a |
| bema_for_reference_model.html | 90 kB | | fe742f97 |
| bema_for_reference_model.md | 7.18 kB | | 67f220ee |
| callbacks.html | 95.8 kB | | b125b2ad |
| callbacks.md | 7.88 kB | | 82b97275 |
| chat_template_utils.html | 46.2 kB | | 0413231c |
| chat_template_utils.md | 5.78 kB | | cc924e85 |
| chat_templates.html | 37.1 kB | | 523c9498 |
| chat_templates.md | 7.04 kB | | cae9eb87 |
| clis.html | 53.4 kB | | fe274339 |
| clis.md | 12.8 kB | | 10fdcc76 |
| community_tutorials.html | 31 kB | | 979ad8a6 |
| community_tutorials.md | 11 kB | | 61ce000b |
| cpo_trainer.html | 145 kB | | b8ecb7b6 |
| cpo_trainer.md | 23.2 kB | | f07a666c |
| customization.html | 31 kB | | 2689cde3 |
| customization.md | 4.08 kB | | 3ae9bda6 |
| data_utils.html | 62.7 kB | | 4536dea6 |
| data_utils.md | 6.87 kB | | e9e71165 |
| dataset_formats.html | 223 kB | | e71f03e8 |
| dataset_formats.md | 43 kB | | 0ebd475e |
| deepspeed_integration.html | 15.8 kB | | e2cbcfd0 |
| deepspeed_integration.md | 1.52 kB | | e5b0fad5 |
| distillation_trainer.html | 161 kB | | 469eec00 |
| distillation_trainer.md | 12.3 kB | | ccff4658 |
| distributing_training.html | 96.5 kB | | 051cba4a |
| distributing_training.md | 21 kB | | 75949925 |
| dpo_trainer.html | 233 kB | | e3881db7 |
| dpo_trainer.md | 30.9 kB | | 4f449072 |
| example_overview.html | 42.7 kB | | ed86586c |
| example_overview.md | 19.7 kB | | 630934e5 |
| experimental_overview.html | 10.8 kB | | a0516754 |
| experimental_overview.md | 1.62 kB | | 45d90cc6 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 85 kB | | 4e0f99ba |
| gfpo.md | 5.24 kB | | 4b4d9ee7 |
| gkd_trainer.html | 119 kB | | 10ebdf95 |
| gkd_trainer.md | 14.1 kB | | 9c6d426e |
| gold_trainer.html | 166 kB | | 29d7f980 |
| gold_trainer.md | 18.1 kB | | 59ff7b17 |
| grpo_trainer.html | 561 kB | | a58f56bf |
| grpo_trainer.md | 61.5 kB | | 572c8d12 |
| grpo_with_replay_buffer.html | 90.3 kB | | 2b2f7928 |
| grpo_with_replay_buffer.md | 6.16 kB | | 59adc904 |
| gspo_token.html | 50.2 kB | | 22b5d063 |
| gspo_token.md | 4.27 kB | | a3235a41 |
| index.html | 29 kB | | 7ff07f60 |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | 0d40096f |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | cee2a9b9 |
| jobs_training.md | 6.46 kB | | cb814663 |
| kernels_hub.html | 26.8 kB | | ae8e116d |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 134 kB | | 3f7ec740 |
| kto_trainer.md | 18.2 kB | | 69712868 |
| liger_kernel_integration.html | 15 kB | | f617abd6 |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 947 kB | | 5d7a80d7 |
| llms.txt | 5.15 kB | | eec5d8c2 |
| lora_without_regret.html | 45 kB | | 1cf0539d |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | 1625fa5d |
| merge_model_callback.md | 1.19 kB | | 30a17587 |
| minillm_trainer.html | 180 kB | | cdd7e873 |
| minillm_trainer.md | 16.4 kB | | 4bf62554 |
| nash_md_trainer.html | 125 kB | | 750d0b22 |
| nash_md_trainer.md | 16.6 kB | | ba5c4c55 |
| nemo_gym.html | 58.5 kB | | e2e85c01 |
| nemo_gym.md | 10.3 kB | | 45caccd9 |
| objects.inv | 2.45 kB | | e668654d |
| online_dpo_trainer.html | 180 kB | | 89813af3 |
| online_dpo_trainer.md | 23.3 kB | | e6eb8908 |
| openenv.html | 114 kB | | 887557e7 |
| openenv.md | 27.8 kB | | 17d29639 |
| orpo_trainer.html | 128 kB | | 2b349129 |
| orpo_trainer.md | 17.9 kB | | 233aa667 |
| paper_index.html | 742 kB | | 5177fccd |
| paper_index.md | 84 kB | | d20b400f |
| papo_trainer.html | 112 kB | | c382af8f |
| papo_trainer.md | 8.82 kB | | 1fabd366 |
| peft_integration.html | 131 kB | | 7ffb33fb |
| peft_integration.md | 23.9 kB | | 6ae8728c |
| ppo_trainer.html | 279 kB | | c9ef4b91 |
| ppo_trainer.md | 41.5 kB | | b0035587 |
| prm_trainer.html | 118 kB | | 78b8fe26 |
| prm_trainer.md | 14.2 kB | | 8002f21c |
| ptt_integration.html | 29.3 kB | | aa4a6f3c |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | 5bdc5013 |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 95.4 kB | | a8fa5fb8 |
| rapidfire_integration.md | 17.8 kB | | b0dd6d2b |
| reducing_memory_usage.html | 57.1 kB | | 2648fb5e |
| reducing_memory_usage.md | 13.7 kB | | 70322b42 |
|