| _app | | | 199 items |
| _toctree.yml | 3.29 kB | | 3ae9d845 |
| async_grpo_trainer.html | 108 kB | | 32009c07 |
| async_grpo_trainer.md | 12.3 kB | | 0e8b14e8 |
| bco_trainer.html | 130 kB | | d49ac802 |
| bco_trainer.md | 14.1 kB | | 8a14359e |
| bema_for_reference_model.html | 90 kB | | 8aa0e67f |
| bema_for_reference_model.md | 7.18 kB | | dc321ee1 |
| callbacks.html | 95.8 kB | | 2b3fba2b |
| callbacks.md | 7.88 kB | | f1ae0b43 |
| chat_template_utils.html | 45.5 kB | | 968ea5b1 |
| chat_template_utils.md | 5.3 kB | | b7c1e757 |
| clis.html | 53.4 kB | | cf5600e6 |
| clis.md | 12.8 kB | | 3fd6c6cb |
| community_tutorials.html | 31 kB | | 7846de88 |
| community_tutorials.md | 11 kB | | b6489b7d |
| cpo_trainer.html | 144 kB | | 5297d770 |
| cpo_trainer.md | 23 kB | | 80c5c7ab |
| customization.html | 31 kB | | dda5d95a |
| customization.md | 4.08 kB | | 57f92c2f |
| data_utils.html | 62.9 kB | | 4e7ac747 |
| data_utils.md | 6.32 kB | | f1d1a651 |
| dataset_formats.html | 223 kB | | ab026bac |
| dataset_formats.md | 40.2 kB | | 53c53e78 |
| deepspeed_integration.html | 15.8 kB | | 5b834bf8 |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distillation_trainer.html | 156 kB | | aecba8be |
| distillation_trainer.md | 12 kB | | 4751fce4 |
| distributing_training.html | 96.5 kB | | 8cae64e2 |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 232 kB | | 48c6b92d |
| dpo_trainer.md | 30.8 kB | | b7422052 |
| example_overview.html | 42.7 kB | | 53658d40 |
| example_overview.md | 19.7 kB | | fd2371df |
| experimental_overview.html | 10.8 kB | | 2aa4ae3f |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 84.4 kB | | 54145a94 |
| gfpo.md | 5.24 kB | | cd0be08e |
| gkd_trainer.html | 119 kB | | 65e03a1c |
| gkd_trainer.md | 14.1 kB | | 6e4e5e40 |
| gold_trainer.html | 166 kB | | 23866416 |
| gold_trainer.md | 18.1 kB | | a3be6c8b |
| grpo_trainer.html | 560 kB | | 258f7455 |
| grpo_trainer.md | 55.4 kB | | 077f66b5 |
| grpo_with_replay_buffer.html | 89.6 kB | | b4e7debf |
| grpo_with_replay_buffer.md | 6.16 kB | | fc92541c |
| gspo_token.html | 50.2 kB | | 509d1e8e |
| gspo_token.md | 4.27 kB | | 1fab3fd9 |
| index.html | 29 kB | | 4c4ca17e |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | 5b7f6ce6 |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | f35157c0 |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| kernels_hub.html | 26.8 kB | | f84ec484 |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 137 kB | | ae2670ee |
| kto_trainer.md | 18.1 kB | | b1214954 |
| liger_kernel_integration.html | 15 kB | | 2767cf23 |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 836 kB | | 0ed3f428 |
| llms.txt | 5 kB | | bcea9fde |
| lora_without_regret.html | 45 kB | | 39475361 |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | 90d86497 |
| merge_model_callback.md | 1.19 kB | | 06e7c149 |
| minillm_trainer.html | 179 kB | | d1ef3381 |
| minillm_trainer.md | 16.4 kB | | 716860f5 |
| nash_md_trainer.html | 124 kB | | ce0cc427 |
| nash_md_trainer.md | 16.3 kB | | a7bd49b2 |
| nemo_gym.html | 58.5 kB | | 818e2ce2 |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.41 kB | | 0f4c56f3 |
| online_dpo_trainer.html | 179 kB | | ae4631ff |
| online_dpo_trainer.md | 23.1 kB | | 01234e3a |
| openenv.html | 114 kB | | f667cb30 |
| openenv.md | 27.8 kB | | 1b59539a |
| orpo_trainer.html | 127 kB | | 69f64345 |
| orpo_trainer.md | 17.7 kB | | e1f61113 |
| paper_index.html | 734 kB | | 07949700 |
| paper_index.md | 19.1 kB | | f56df1f8 |
| papo_trainer.html | 111 kB | | 78d986c2 |
| papo_trainer.md | 8.82 kB | | df1ffd89 |
| peft_integration.html | 131 kB | | 9627b179 |
| peft_integration.md | 23.9 kB | | c63833a2 |
| ppo_trainer.html | 278 kB | | 1412dbe2 |
| ppo_trainer.md | 41.4 kB | | bbab4a31 |
| prm_trainer.html | 117 kB | | c707a1b4 |
| prm_trainer.md | 13.9 kB | | a8216fa7 |
| ptt_integration.html | 29.3 kB | | d4d5dd7f |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | 9fc6a646 |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 81.1 kB | | 7ef36b11 |
| rapidfire_integration.md | 12.8 kB | | 78b07e81 |
| reducing_memory_usage.html | 52.4 kB | | 8da089e2 |
| reducing_memory_usage.md | 12.3 kB | | d61af82e |
| reward_trainer.html | 175 kB | | f128c353 |
| reward_trainer.md | 21.5 kB | | d09ee490 |
|