| _app | | | 137 items |
| _toctree.yml | 3.38 kB | | 9da8f3eb |
| async_grpo_trainer.html | 108 kB | | da3c13c1 |
| async_grpo_trainer.md | 12.3 kB | | f793442d |
| bco_trainer.html | 130 kB | | def18c68 |
| bco_trainer.md | 14.1 kB | | b20c7a1a |
| bema_for_reference_model.html | 90 kB | | 93676d61 |
| bema_for_reference_model.md | 7.18 kB | | 875245b3 |
| callbacks.html | 95.8 kB | | 39949928 |
| callbacks.md | 7.88 kB | | 812267c4 |
| chat_template_utils.html | 45.9 kB | | 2fbc10fc |
| chat_template_utils.md | 5.52 kB | | 6d80e676 |
| chat_templates.html | 33.5 kB | | c332dc92 |
| chat_templates.md | 6.03 kB | | dee2f91d |
| clis.html | 53.4 kB | | 6f165c7c |
| clis.md | 12.8 kB | | 4db41eb7 |
| community_tutorials.html | 31 kB | | 17c2dadf |
| community_tutorials.md | 10.9 kB | | f776965d |
| cpo_trainer.html | 144 kB | | 7e08b782 |
| cpo_trainer.md | 23 kB | | baa666fb |
| customization.html | 30.9 kB | | f95b5516 |
| customization.md | 4.04 kB | | f7ac417d |
| data_utils.html | 62.7 kB | | b0636fdc |
| data_utils.md | 6.87 kB | | 71b03b71 |
| dataset_formats.html | 223 kB | | b4607bba |
| dataset_formats.md | 40.1 kB | | 76ee96f2 |
| deepspeed_integration.html | 15.8 kB | | e03b88fc |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distillation_trainer.html | 161 kB | | 68359a0b |
| distillation_trainer.md | 12.3 kB | | 302bae8a |
| distributing_training.html | 96.5 kB | | 83ea4e74 |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 232 kB | | bf6213d2 |
| dpo_trainer.md | 30.7 kB | | 8ceee54d |
| example_overview.html | 42.7 kB | | e81125f7 |
| example_overview.md | 19.6 kB | | e38f378d |
| experimental_overview.html | 10.8 kB | | 15e4ed09 |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 85 kB | | 0206aa83 |
| gfpo.md | 5.24 kB | | 00e98358 |
| gkd_trainer.html | 119 kB | | 3155c728 |
| gkd_trainer.md | 14.1 kB | | d428137e |
| gold_trainer.html | 166 kB | | d9db7891 |
| gold_trainer.md | 18.1 kB | | cf6a6156 |
| grpo_trainer.html | 561 kB | | 716ef841 |
| grpo_trainer.md | 55.8 kB | | 65d231f6 |
| grpo_with_replay_buffer.html | 90.3 kB | | 3c4e9670 |
| grpo_with_replay_buffer.md | 6.16 kB | | 1cbccca0 |
| gspo_token.html | 50.2 kB | | 870bda81 |
| gspo_token.md | 4.27 kB | | 469d97cd |
| index.html | 29 kB | | 9903caaf |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | 240a5b7d |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | c1edf51e |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| kernels_hub.html | 26.8 kB | | e1efe9fd |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 138 kB | | 30de152a |
| kto_trainer.md | 18.3 kB | | e6d9ed09 |
| liger_kernel_integration.html | 15 kB | | 86af0fbf |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 867 kB | | 1b9e6610 |
| llms.txt | 5.15 kB | | 6b36f770 |
| lora_without_regret.html | 45 kB | | 98ed3a99 |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | 4daeddde |
| merge_model_callback.md | 1.19 kB | | b7ae2496 |
| minillm_trainer.html | 180 kB | | 112023cd |
| minillm_trainer.md | 16.4 kB | | 43d30fce |
| nash_md_trainer.html | 125 kB | | 531f6d3d |
| nash_md_trainer.md | 16.3 kB | | 82b9b4ea |
| nemo_gym.html | 58.5 kB | | 6fba14e4 |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.44 kB | | 382bd510 |
| online_dpo_trainer.html | 180 kB | | 0d5d951c |
| online_dpo_trainer.md | 23.1 kB | | 6aaeee88 |
| openenv.html | 114 kB | | 504d356a |
| openenv.md | 27.8 kB | | f91f3c11 |
| orpo_trainer.html | 127 kB | | 12d1bbcc |
| orpo_trainer.md | 17.7 kB | | 77a042e8 |
| paper_index.html | 742 kB | | 87dbb9b7 |
| paper_index.md | 19.1 kB | | 38fb40b2 |
| papo_trainer.html | 112 kB | | d656b0e1 |
| papo_trainer.md | 8.82 kB | | 9c2cb16b |
| peft_integration.html | 131 kB | | 9ae60a75 |
| peft_integration.md | 23.9 kB | | b7b70b52 |
| ppo_trainer.html | 279 kB | | cb7fdd97 |
| ppo_trainer.md | 41.4 kB | | 7e3b6421 |
| prm_trainer.html | 118 kB | | e5f5fff8 |
| prm_trainer.md | 13.9 kB | | ab8eaa66 |
| ptt_integration.html | 29.3 kB | | bfbab71c |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | 8009b251 |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 95.4 kB | | 53a6a2e3 |
| rapidfire_integration.md | 17.7 kB | | 08fed5af |
| reducing_memory_usage.html | 52.4 kB | | 44b8989a |
| reducing_memory_usage.md | 12.3 kB | | d61af82e |
|