| _app | | | 150 items |
| _toctree.yml | 3.29 kB | | 3ae9d845 |
| async_grpo_trainer.html | 108 kB | | 91003728 |
| async_grpo_trainer.md | 12.3 kB | | ada3ab89 |
| bco_trainer.html | 130 kB | | 3f8e5e8c |
| bco_trainer.md | 14.1 kB | | f5e046c3 |
| bema_for_reference_model.html | 90 kB | | 4d2176c5 |
| bema_for_reference_model.md | 7.18 kB | | 628de72c |
| callbacks.html | 95.8 kB | | 49a640b5 |
| callbacks.md | 7.88 kB | | d08d521d |
| chat_template_utils.html | 45.7 kB | | ff0a3e98 |
| chat_template_utils.md | 5.34 kB | | d15242ac |
| clis.html | 53.4 kB | | c46062c6 |
| clis.md | 12.8 kB | | 5b1e4c49 |
| community_tutorials.html | 31 kB | | 1c52b46c |
| community_tutorials.md | 11 kB | | f58c7b9e |
| cpo_trainer.html | 144 kB | | 944e2e4e |
| cpo_trainer.md | 23 kB | | 91667c62 |
| customization.html | 31 kB | | 76922abe |
| customization.md | 4.08 kB | | af29f8d5 |
| data_utils.html | 62.9 kB | | 09c07817 |
| data_utils.md | 6.32 kB | | 55dc5579 |
| dataset_formats.html | 223 kB | | e0a81f80 |
| dataset_formats.md | 40.2 kB | | 2789b70a |
| deepspeed_integration.html | 15.8 kB | | 6bb0cb96 |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distillation_trainer.html | 160 kB | | 515b714a |
| distillation_trainer.md | 12.3 kB | | 1032e829 |
| distributing_training.html | 96.5 kB | | 8cf003d3 |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 232 kB | | 96b2efc9 |
| dpo_trainer.md | 30.8 kB | | 9bd7e687 |
| example_overview.html | 42.7 kB | | f6ec6a2d |
| example_overview.md | 19.7 kB | | 84c2d57b |
| experimental_overview.html | 10.8 kB | | 0bdb7641 |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 84.4 kB | | d33bfe75 |
| gfpo.md | 5.24 kB | | ca48be2c |
| gkd_trainer.html | 119 kB | | 6286e2d7 |
| gkd_trainer.md | 14.1 kB | | 3a610999 |
| gold_trainer.html | 166 kB | | 97b1cfda |
| gold_trainer.md | 18.1 kB | | 355ce4ad |
| grpo_trainer.html | 560 kB | | 3aa794b7 |
| grpo_trainer.md | 55.4 kB | | ba0c8c88 |
| grpo_with_replay_buffer.html | 89.6 kB | | 7b6b761e |
| grpo_with_replay_buffer.md | 6.16 kB | | 89e1329b |
| gspo_token.html | 50.2 kB | | a1ae5629 |
| gspo_token.md | 4.27 kB | | c45a58ad |
| index.html | 29 kB | | b263690d |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | 0485f952 |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | 61a53517 |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| kernels_hub.html | 26.8 kB | | 64f82fe9 |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 137 kB | | 728b4cea |
| kto_trainer.md | 18.1 kB | | ed140b40 |
| liger_kernel_integration.html | 15 kB | | 86fd92ca |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 836 kB | | df8a4b5e |
| llms.txt | 5 kB | | 2663efa4 |
| lora_without_regret.html | 45 kB | | ac4a2619 |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | 7147108b |
| merge_model_callback.md | 1.19 kB | | 17e67ac3 |
| minillm_trainer.html | 179 kB | | 59e2b41d |
| minillm_trainer.md | 16.4 kB | | 32bfad4e |
| nash_md_trainer.html | 124 kB | | 9703def8 |
| nash_md_trainer.md | 16.3 kB | | 71b2879c |
| nemo_gym.html | 58.5 kB | | d98c7791 |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.41 kB | | 7b954e1b |
| online_dpo_trainer.html | 179 kB | | aaefba0f |
| online_dpo_trainer.md | 23.1 kB | | a415caa9 |
| openenv.html | 114 kB | | 3d28ee9f |
| openenv.md | 27.8 kB | | 98d3bba7 |
| orpo_trainer.html | 127 kB | | 9ddd09cd |
| orpo_trainer.md | 17.7 kB | | 7a9928eb |
| paper_index.html | 734 kB | | 19179ba4 |
| paper_index.md | 19.1 kB | | e3059dcd |
| papo_trainer.html | 111 kB | | 326dcea7 |
| papo_trainer.md | 8.82 kB | | f3ad2dc6 |
| peft_integration.html | 131 kB | | c2d89f79 |
| peft_integration.md | 23.9 kB | | 792dfb23 |
| ppo_trainer.html | 278 kB | | fd24e02b |
| ppo_trainer.md | 41.4 kB | | b2e81e77 |
| prm_trainer.html | 117 kB | | 25c617ca |
| prm_trainer.md | 13.9 kB | | ea1e5b2f |
| ptt_integration.html | 29.3 kB | | c9f58f75 |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | 25b363c5 |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 81.1 kB | | 8e67dbf6 |
| rapidfire_integration.md | 12.8 kB | | 78b07e81 |
| reducing_memory_usage.html | 52.4 kB | | a32688af |
| reducing_memory_usage.md | 12.3 kB | | d61af82e |
| reward_trainer.html | 175 kB | | 7ffce5c7 |
| reward_trainer.md | 21.5 kB | | 57407bbd |
|