| _app | | | 228 items |
| _toctree.yml | 3.38 kB | | 9da8f3eb |
| async_grpo_trainer.html | 108 kB | | 0a9c7c44 |
| async_grpo_trainer.md | 12.3 kB | | ab704719 |
| bco_trainer.html | 130 kB | | 7dc62f65 |
| bco_trainer.md | 14.1 kB | | 2de3c2c8 |
| bema_for_reference_model.html | 90 kB | | 60541558 |
| bema_for_reference_model.md | 7.18 kB | | edd01856 |
| callbacks.html | 95.8 kB | | 9dafabc1 |
| callbacks.md | 7.88 kB | | 440581a4 |
| chat_template_utils.html | 46.2 kB | | b1ddb0bd |
| chat_template_utils.md | 5.76 kB | | d2abf885 |
| chat_templates.html | 33.5 kB | | 228816bf |
| chat_templates.md | 6.03 kB | | cbd38070 |
| clis.html | 53.4 kB | | a3e96f84 |
| clis.md | 12.8 kB | | 1e666408 |
| community_tutorials.html | 31 kB | | d40fc435 |
| community_tutorials.md | 10.9 kB | | 93806212 |
| cpo_trainer.html | 144 kB | | 07662bd0 |
| cpo_trainer.md | 23 kB | | e0582596 |
| customization.html | 30.9 kB | | a70d0892 |
| customization.md | 4.04 kB | | ef9ae6e5 |
| data_utils.html | 62.7 kB | | 0caad94f |
| data_utils.md | 6.87 kB | | a4446fe8 |
| dataset_formats.html | 223 kB | | bd1f2565 |
| dataset_formats.md | 40.1 kB | | 08f8a978 |
| deepspeed_integration.html | 15.8 kB | | c72dc673 |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distillation_trainer.html | 161 kB | | 1633fb4e |
| distillation_trainer.md | 12.3 kB | | 8ac404c4 |
| distributing_training.html | 96.5 kB | | 628ccb8a |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 232 kB | | e09489d3 |
| dpo_trainer.md | 30.7 kB | | 37c76a53 |
| example_overview.html | 42.7 kB | | c6fcefd5 |
| example_overview.md | 19.6 kB | | d7cf59eb |
| experimental_overview.html | 10.8 kB | | b856ff2b |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 85 kB | | 6cd6dd05 |
| gfpo.md | 5.24 kB | | f9c1467e |
| gkd_trainer.html | 119 kB | | 0b6be1f2 |
| gkd_trainer.md | 14.1 kB | | fc4ac3d5 |
| gold_trainer.html | 166 kB | | 46d6c8d7 |
| gold_trainer.md | 18.1 kB | | 96c60db3 |
| grpo_trainer.html | 561 kB | | 52175148 |
| grpo_trainer.md | 55.8 kB | | bdbe27c4 |
| grpo_with_replay_buffer.html | 90.3 kB | | 5c8781c1 |
| grpo_with_replay_buffer.md | 6.16 kB | | 3ce967ae |
| gspo_token.html | 50.2 kB | | 23c5be64 |
| gspo_token.md | 4.27 kB | | 179b0ad0 |
| index.html | 29 kB | | bf48f74f |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | d8dc0d56 |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | 5a4036bd |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| kernels_hub.html | 26.8 kB | | c67e615f |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 138 kB | | d00369d8 |
| kto_trainer.md | 18.3 kB | | 9a908458 |
| liger_kernel_integration.html | 15 kB | | ad780884 |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 867 kB | | baecaea9 |
| llms.txt | 5.15 kB | | 5f9ff0e5 |
| lora_without_regret.html | 45 kB | | 3a31829a |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | 05ec07e4 |
| merge_model_callback.md | 1.19 kB | | 52842476 |
| minillm_trainer.html | 180 kB | | 450cdac2 |
| minillm_trainer.md | 16.4 kB | | 75afbd09 |
| nash_md_trainer.html | 125 kB | | 3866236b |
| nash_md_trainer.md | 16.3 kB | | 1525a9eb |
| nemo_gym.html | 58.5 kB | | 74717323 |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.44 kB | | f6e9a700 |
| online_dpo_trainer.html | 180 kB | | ad42b7d0 |
| online_dpo_trainer.md | 23.1 kB | | 4d162eff |
| openenv.html | 114 kB | | 459b0c82 |
| openenv.md | 27.8 kB | | e05ccf1b |
| orpo_trainer.html | 127 kB | | e91d3850 |
| orpo_trainer.md | 17.7 kB | | 099cc2db |
| paper_index.html | 742 kB | | 530197cd |
| paper_index.md | 19.1 kB | | 7732cf6d |
| papo_trainer.html | 112 kB | | e0de0f58 |
| papo_trainer.md | 8.82 kB | | f44e8f20 |
| peft_integration.html | 131 kB | | 9b77893e |
| peft_integration.md | 23.9 kB | | 99a956b6 |
| ppo_trainer.html | 279 kB | | 408cdb90 |
| ppo_trainer.md | 41.4 kB | | c893b0dd |
| prm_trainer.html | 118 kB | | dbb40087 |
| prm_trainer.md | 13.9 kB | | 8764cebd |
| ptt_integration.html | 29.3 kB | | 60fec5db |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | 5eca8242 |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 95.4 kB | | 116f988b |
| rapidfire_integration.md | 17.7 kB | | 08fed5af |
| reducing_memory_usage.html | 52.4 kB | | 89f1766c |
| reducing_memory_usage.md | 12.3 kB | | d61af82e |
|