| _app | | | 237 items |
| _toctree.yml | 3.29 kB | | 3ae9d845 |
| async_grpo_trainer.html | 108 kB | | 990da835 |
| async_grpo_trainer.md | 12.3 kB | | 2dca8eb6 |
| bco_trainer.html | 130 kB | | 8545a7be |
| bco_trainer.md | 14.1 kB | | cb0d8667 |
| bema_for_reference_model.html | 90 kB | | 825a40a1 |
| bema_for_reference_model.md | 7.18 kB | | 6dc182be |
| callbacks.html | 95.8 kB | | d9233b8e |
| callbacks.md | 7.88 kB | | a74d6792 |
| chat_template_utils.html | 45.5 kB | | 4e3c1e1e |
| chat_template_utils.md | 5.3 kB | | e91b7850 |
| clis.html | 53.4 kB | | 5454623d |
| clis.md | 12.8 kB | | 17cff2d0 |
| community_tutorials.html | 31 kB | | 2ab70284 |
| community_tutorials.md | 11 kB | | a3a7afad |
| cpo_trainer.html | 144 kB | | a66792bb |
| cpo_trainer.md | 23 kB | | 8d61b4fa |
| customization.html | 31 kB | | fe6ef426 |
| customization.md | 4.08 kB | | 401aa005 |
| data_utils.html | 62.9 kB | | 20640eb2 |
| data_utils.md | 6.32 kB | | 90987807 |
| dataset_formats.html | 223 kB | | 5f805f34 |
| dataset_formats.md | 40.2 kB | | 5f7bb19f |
| deepspeed_integration.html | 15.8 kB | | 2a4f8579 |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distillation_trainer.html | 160 kB | | ae352977 |
| distillation_trainer.md | 12.3 kB | | 35e2645d |
| distributing_training.html | 96.5 kB | | 315aa52a |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 232 kB | | 5d1a4694 |
| dpo_trainer.md | 30.8 kB | | b10a5bf1 |
| example_overview.html | 42.7 kB | | de7c3b81 |
| example_overview.md | 19.7 kB | | 13832f8c |
| experimental_overview.html | 10.8 kB | | b8504b83 |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 84.4 kB | | 27e3f503 |
| gfpo.md | 5.24 kB | | 3df5c2f2 |
| gkd_trainer.html | 119 kB | | ed78df4c |
| gkd_trainer.md | 14.1 kB | | ea508b73 |
| gold_trainer.html | 166 kB | | 1ede16e8 |
| gold_trainer.md | 18.1 kB | | f3e62acb |
| grpo_trainer.html | 559 kB | | 1e8a2508 |
| grpo_trainer.md | 55.2 kB | | a8b236bf |
| grpo_with_replay_buffer.html | 89.6 kB | | a2a23c96 |
| grpo_with_replay_buffer.md | 6.16 kB | | 702073a6 |
| gspo_token.html | 50.2 kB | | 7f7ad887 |
| gspo_token.md | 4.27 kB | | 7b122c5e |
| index.html | 29 kB | | 15c99f96 |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | 22308818 |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | 5934f314 |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| kernels_hub.html | 26.8 kB | | d2091171 |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 142 kB | | 237ba2ec |
| kto_trainer.md | 18.4 kB | | 032c2f25 |
| liger_kernel_integration.html | 15 kB | | 4b447bf5 |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 836 kB | | 65da7c68 |
| llms.txt | 5 kB | | f36d9e3c |
| lora_without_regret.html | 45 kB | | f743fa51 |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | 3fa55e21 |
| merge_model_callback.md | 1.19 kB | | 6d9d3897 |
| minillm_trainer.html | 179 kB | | c04c3488 |
| minillm_trainer.md | 16.4 kB | | a141f540 |
| nash_md_trainer.html | 124 kB | | 760c4ea4 |
| nash_md_trainer.md | 16.3 kB | | 8b09b56d |
| nemo_gym.html | 58.5 kB | | f3cab670 |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.41 kB | | 00fe2542 |
| online_dpo_trainer.html | 179 kB | | dbda5e07 |
| online_dpo_trainer.md | 23.1 kB | | ba8141f9 |
| openenv.html | 114 kB | | ac88522b |
| openenv.md | 27.8 kB | | 4439dc3f |
| orpo_trainer.html | 127 kB | | 9851e571 |
| orpo_trainer.md | 17.7 kB | | 30e3987d |
| paper_index.html | 734 kB | | 9b46ba13 |
| paper_index.md | 19.1 kB | | 34a0ee48 |
| papo_trainer.html | 111 kB | | 43c69924 |
| papo_trainer.md | 8.82 kB | | 0a00ed61 |
| peft_integration.html | 131 kB | | 911cf92a |
| peft_integration.md | 23.9 kB | | e2ad1f79 |
| ppo_trainer.html | 278 kB | | 3c83c47a |
| ppo_trainer.md | 41.4 kB | | b8297d3f |
| prm_trainer.html | 117 kB | | 5aa6d3c8 |
| prm_trainer.md | 13.9 kB | | ef8b48e4 |
| ptt_integration.html | 29.3 kB | | db84adcd |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | 48366b79 |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 81.1 kB | | 08b90822 |
| rapidfire_integration.md | 12.8 kB | | 78b07e81 |
| reducing_memory_usage.html | 52.4 kB | | 40f64c4c |
| reducing_memory_usage.md | 12.3 kB | | d61af82e |
| reward_trainer.html | 175 kB | | daf2f649 |
| reward_trainer.md | 21.5 kB | | fd592ab9 |
|