| _app | | | 141 items |
| _toctree.yml | 3.29 kB | | 3ae9d845 |
| async_grpo_trainer.html | 108 kB | | 6a7294eb |
| async_grpo_trainer.md | 12.3 kB | | 4fbb5b5b |
| bco_trainer.html | 130 kB | | e5a32a30 |
| bco_trainer.md | 14.1 kB | | 5b1179dc |
| bema_for_reference_model.html | 90 kB | | 0f328afa |
| bema_for_reference_model.md | 7.18 kB | | 64ebfde1 |
| callbacks.html | 95.8 kB | | 5d7ec955 |
| callbacks.md | 7.88 kB | | f7493e3c |
| chat_template_utils.html | 45.7 kB | | 096df612 |
| chat_template_utils.md | 5.34 kB | | 72a04a08 |
| clis.html | 53.4 kB | | 75572e46 |
| clis.md | 12.8 kB | | 5267ba17 |
| community_tutorials.html | 31 kB | | 03e39e4d |
| community_tutorials.md | 11 kB | | 4ac524ac |
| cpo_trainer.html | 144 kB | | 55bb4e8b |
| cpo_trainer.md | 23 kB | | 028462e8 |
| customization.html | 31 kB | | 6983573d |
| customization.md | 4.08 kB | | 8b868383 |
| data_utils.html | 62.9 kB | | 6b44b6f6 |
| data_utils.md | 6.32 kB | | e53f51b0 |
| dataset_formats.html | 223 kB | | 27a5e371 |
| dataset_formats.md | 40.2 kB | | 796d85c1 |
| deepspeed_integration.html | 15.8 kB | | be27823a |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distillation_trainer.html | 160 kB | | 5102497f |
| distillation_trainer.md | 12.3 kB | | 02935781 |
| distributing_training.html | 96.5 kB | | 8b1be3f7 |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 232 kB | | 0906b32e |
| dpo_trainer.md | 30.8 kB | | 17735985 |
| example_overview.html | 42.7 kB | | 8f54e103 |
| example_overview.md | 19.7 kB | | 5db1d3b0 |
| experimental_overview.html | 10.8 kB | | fe09fddf |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 84.4 kB | | 686281c5 |
| gfpo.md | 5.24 kB | | 19683202 |
| gkd_trainer.html | 119 kB | | a93d0733 |
| gkd_trainer.md | 14.1 kB | | 892a1c2f |
| gold_trainer.html | 166 kB | | 67acbb19 |
| gold_trainer.md | 18.1 kB | | 8ab8f20e |
| grpo_trainer.html | 560 kB | | 99acf0b9 |
| grpo_trainer.md | 55.4 kB | | d0717073 |
| grpo_with_replay_buffer.html | 89.6 kB | | 16be7205 |
| grpo_with_replay_buffer.md | 6.16 kB | | b5e56cc3 |
| gspo_token.html | 50.2 kB | | a5e3f28c |
| gspo_token.md | 4.27 kB | | 04a1df74 |
| index.html | 29 kB | | 5bb691f2 |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | 0d875807 |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | a89ce87d |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| kernels_hub.html | 26.8 kB | | 6ebe6d65 |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 137 kB | | 0ddf4576 |
| kto_trainer.md | 18.1 kB | | a78e6b23 |
| liger_kernel_integration.html | 15 kB | | 2777f01a |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 836 kB | | 207fb85f |
| llms.txt | 5 kB | | 8636d320 |
| lora_without_regret.html | 45 kB | | b3cc447f |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | 028bd8d5 |
| merge_model_callback.md | 1.19 kB | | 6ff744d9 |
| minillm_trainer.html | 179 kB | | ad46a98f |
| minillm_trainer.md | 16.4 kB | | 03582966 |
| nash_md_trainer.html | 124 kB | | 5fdf26db |
| nash_md_trainer.md | 16.3 kB | | 361fee93 |
| nemo_gym.html | 58.5 kB | | c6b9d65e |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.41 kB | | f3e37181 |
| online_dpo_trainer.html | 179 kB | | 1dcc5241 |
| online_dpo_trainer.md | 23.1 kB | | 79e2dc5f |
| openenv.html | 114 kB | | b027ec7a |
| openenv.md | 27.8 kB | | c0610fe3 |
| orpo_trainer.html | 127 kB | | 41a1c204 |
| orpo_trainer.md | 17.7 kB | | 80a376be |
| paper_index.html | 734 kB | | 2aacecd9 |
| paper_index.md | 19.1 kB | | 20ba55bd |
| papo_trainer.html | 111 kB | | f93ff59b |
| papo_trainer.md | 8.82 kB | | 8fb06bf3 |
| peft_integration.html | 131 kB | | 3a1c6bed |
| peft_integration.md | 23.9 kB | | dce3fb2c |
| ppo_trainer.html | 278 kB | | 62b0b1c8 |
| ppo_trainer.md | 41.4 kB | | 7e3544e5 |
| prm_trainer.html | 117 kB | | 1070e902 |
| prm_trainer.md | 13.9 kB | | 8610a2e6 |
| ptt_integration.html | 29.3 kB | | 261070eb |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | 81f7b7c6 |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 81.1 kB | | 218409b9 |
| rapidfire_integration.md | 12.8 kB | | 78b07e81 |
| reducing_memory_usage.html | 52.4 kB | | 41ebe931 |
| reducing_memory_usage.md | 12.3 kB | | d61af82e |
| reward_trainer.html | 175 kB | | 9fce7acf |
| reward_trainer.md | 21.5 kB | | 6b5bc12e |
|