| _app | | | 144 items |
| _toctree.yml | 3.38 kB | | 9da8f3eb |
| async_grpo_trainer.html | 108 kB | | a7cc5a55 |
| async_grpo_trainer.md | 12.3 kB | | ef59bfd7 |
| bco_trainer.html | 130 kB | | d37f5e88 |
| bco_trainer.md | 14.1 kB | | bf76a04e |
| bema_for_reference_model.html | 90 kB | | 0946453d |
| bema_for_reference_model.md | 7.18 kB | | 306e8368 |
| callbacks.html | 95.8 kB | | 4f35ba17 |
| callbacks.md | 7.88 kB | | 86e1cd43 |
| chat_template_utils.html | 46.2 kB | | c02766f2 |
| chat_template_utils.md | 5.76 kB | | 76d196bb |
| chat_templates.html | 33.5 kB | | 2ce942fa |
| chat_templates.md | 6.03 kB | | 32c55d53 |
| clis.html | 53.4 kB | | e18e8c1b |
| clis.md | 12.8 kB | | c2ce5bde |
| community_tutorials.html | 31 kB | | 7985c436 |
| community_tutorials.md | 11 kB | | 57fb3e36 |
| cpo_trainer.html | 144 kB | | bca42a8c |
| cpo_trainer.md | 23 kB | | e13bc1a7 |
| customization.html | 31 kB | | bfbc98e3 |
| customization.md | 4.08 kB | | f8e80391 |
| data_utils.html | 62.7 kB | | 0e71949d |
| data_utils.md | 6.87 kB | | 443b6611 |
| dataset_formats.html | 223 kB | | 267aed06 |
| dataset_formats.md | 40.2 kB | | 9ce29eee |
| deepspeed_integration.html | 15.8 kB | | f2af0f72 |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distillation_trainer.html | 161 kB | | 7c45c9a2 |
| distillation_trainer.md | 12.3 kB | | d54bdd29 |
| distributing_training.html | 96.5 kB | | fc813282 |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 233 kB | | df3affb6 |
| dpo_trainer.md | 30.8 kB | | 9193997d |
| example_overview.html | 42.8 kB | | 8cf9d383 |
| example_overview.md | 19.7 kB | | 49eab583 |
| experimental_overview.html | 10.8 kB | | db747afc |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 85 kB | | 2628e8df |
| gfpo.md | 5.24 kB | | 96e5de9c |
| gkd_trainer.html | 119 kB | | fb787027 |
| gkd_trainer.md | 14.1 kB | | 6fefc831 |
| gold_trainer.html | 166 kB | | 77b327f9 |
| gold_trainer.md | 18.1 kB | | e20dca63 |
| grpo_trainer.html | 561 kB | | 1e2c1f36 |
| grpo_trainer.md | 55.8 kB | | fc593e59 |
| grpo_with_replay_buffer.html | 90.3 kB | | abefd144 |
| grpo_with_replay_buffer.md | 6.16 kB | | 55489817 |
| gspo_token.html | 50.2 kB | | c1803e1d |
| gspo_token.md | 4.27 kB | | 7ca97dcd |
| index.html | 29 kB | | 6589d50d |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | b3795f56 |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | 59b26706 |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| kernels_hub.html | 26.8 kB | | 7356107b |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 138 kB | | b4e6c022 |
| kto_trainer.md | 18.3 kB | | 436372fb |
| liger_kernel_integration.html | 15 kB | | 77e7a893 |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 868 kB | | b324b29b |
| llms.txt | 5.15 kB | | f4585932 |
| lora_without_regret.html | 45 kB | | 90a51dde |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | 9ec6401e |
| merge_model_callback.md | 1.19 kB | | ca7025ff |
| minillm_trainer.html | 180 kB | | 62797ad4 |
| minillm_trainer.md | 16.4 kB | | fdcccc56 |
| nash_md_trainer.html | 125 kB | | 3efebe23 |
| nash_md_trainer.md | 16.3 kB | | be7f927b |
| nemo_gym.html | 58.5 kB | | 4afa4d7b |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.45 kB | | 6ffb61c8 |
| online_dpo_trainer.html | 180 kB | | 77e7c80c |
| online_dpo_trainer.md | 23.1 kB | | 0f0bfcd5 |
| openenv.html | 114 kB | | d3ebcc75 |
| openenv.md | 27.8 kB | | 7470baed |
| orpo_trainer.html | 127 kB | | 18ca8813 |
| orpo_trainer.md | 17.7 kB | | b10d71ba |
| paper_index.html | 742 kB | | 5c413960 |
| paper_index.md | 19.1 kB | | 46d15013 |
| papo_trainer.html | 112 kB | | d6c1d7d7 |
| papo_trainer.md | 8.82 kB | | 09c52031 |
| peft_integration.html | 131 kB | | a7c99674 |
| peft_integration.md | 23.9 kB | | b3ba5341 |
| ppo_trainer.html | 279 kB | | d8b6dfe2 |
| ppo_trainer.md | 41.4 kB | | 9119e975 |
| prm_trainer.html | 118 kB | | 93f897de |
| prm_trainer.md | 13.9 kB | | 1dbacdc5 |
| ptt_integration.html | 29.3 kB | | a08e607f |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | 35bebdcf |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 95.4 kB | | c1b5bec4 |
| rapidfire_integration.md | 17.7 kB | | 08fed5af |
| reducing_memory_usage.html | 52.4 kB | | 8804baa0 |
| reducing_memory_usage.md | 12.3 kB | | d61af82e |
|