| _app | | | 143 items |
| _toctree.yml | 3.38 kB | | 9da8f3eb |
| async_grpo_trainer.html | 108 kB | | a59fe098 |
| async_grpo_trainer.md | 12.3 kB | | cfc25378 |
| bco_trainer.html | 130 kB | | 2ad289b5 |
| bco_trainer.md | 14.1 kB | | 9efeb67f |
| bema_for_reference_model.html | 90 kB | | c9b00ebb |
| bema_for_reference_model.md | 7.18 kB | | 5ed7cb10 |
| callbacks.html | 95.8 kB | | d1c5d8ec |
| callbacks.md | 7.88 kB | | cfaf9551 |
| chat_template_utils.html | 46.2 kB | | 1e875644 |
| chat_template_utils.md | 5.76 kB | | 14130a60 |
| chat_templates.html | 33.5 kB | | 96a71c2d |
| chat_templates.md | 6.03 kB | | cd7edd88 |
| clis.html | 53.4 kB | | 6322237d |
| clis.md | 12.8 kB | | aba96a3c |
| community_tutorials.html | 31 kB | | 990e9a05 |
| community_tutorials.md | 11 kB | | 7c9a3cdf |
| cpo_trainer.html | 144 kB | | 5cc7629d |
| cpo_trainer.md | 23 kB | | 3dff2f5f |
| customization.html | 31 kB | | 8fd98b3e |
| customization.md | 4.08 kB | | 48e1dd2d |
| data_utils.html | 62.7 kB | | 9ab88fd6 |
| data_utils.md | 6.87 kB | | 6f960d1c |
| dataset_formats.html | 223 kB | | d03bbda0 |
| dataset_formats.md | 40.2 kB | | c8da3ebb |
| deepspeed_integration.html | 15.8 kB | | d31e8972 |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distillation_trainer.html | 161 kB | | bb967218 |
| distillation_trainer.md | 12.3 kB | | 364b2d89 |
| distributing_training.html | 96.5 kB | | 076be63f |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 233 kB | | 62a8179d |
| dpo_trainer.md | 30.8 kB | | d947e490 |
| example_overview.html | 42.8 kB | | d0c4bbd4 |
| example_overview.md | 19.7 kB | | 35d9cdde |
| experimental_overview.html | 10.8 kB | | 7c060064 |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 85 kB | | cf636eef |
| gfpo.md | 5.24 kB | | c0eabfe9 |
| gkd_trainer.html | 119 kB | | 8c93ad62 |
| gkd_trainer.md | 14.1 kB | | 6715d5a3 |
| gold_trainer.html | 166 kB | | 67036f64 |
| gold_trainer.md | 18.1 kB | | 4578669e |
| grpo_trainer.html | 561 kB | | 8ff79686 |
| grpo_trainer.md | 55.8 kB | | 470276b5 |
| grpo_with_replay_buffer.html | 90.3 kB | | 12173798 |
| grpo_with_replay_buffer.md | 6.16 kB | | 33e251eb |
| gspo_token.html | 50.2 kB | | 3ed7fbb0 |
| gspo_token.md | 4.27 kB | | 4e8c4209 |
| index.html | 29 kB | | 0f282848 |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | c64836c7 |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | 157f42fa |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| kernels_hub.html | 26.8 kB | | 34660cf4 |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 138 kB | | de378954 |
| kto_trainer.md | 18.3 kB | | 34e20219 |
| liger_kernel_integration.html | 15 kB | | 55614c3d |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 868 kB | | c5f56748 |
| llms.txt | 5.15 kB | | 3ee04e76 |
| lora_without_regret.html | 45 kB | | e14cacbb |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | f1d0c457 |
| merge_model_callback.md | 1.19 kB | | dad5466c |
| minillm_trainer.html | 180 kB | | a9e51fbe |
| minillm_trainer.md | 16.4 kB | | 55724b55 |
| nash_md_trainer.html | 125 kB | | d7d0c92f |
| nash_md_trainer.md | 16.3 kB | | c97c02e3 |
| nemo_gym.html | 58.5 kB | | 0bd50831 |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.45 kB | | 4c0c54ea |
| online_dpo_trainer.html | 180 kB | | fe11cc03 |
| online_dpo_trainer.md | 23.1 kB | | 8ebe387e |
| openenv.html | 114 kB | | ab6d5d7a |
| openenv.md | 27.8 kB | | 8c233b4b |
| orpo_trainer.html | 127 kB | | ff556464 |
| orpo_trainer.md | 17.7 kB | | 4f70e7f3 |
| paper_index.html | 742 kB | | 8f74857f |
| paper_index.md | 19.1 kB | | 4deafb95 |
| papo_trainer.html | 112 kB | | c06b41ea |
| papo_trainer.md | 8.82 kB | | 01b07a01 |
| peft_integration.html | 131 kB | | 3253bb79 |
| peft_integration.md | 23.9 kB | | 49ff4a26 |
| ppo_trainer.html | 279 kB | | 6465cdcf |
| ppo_trainer.md | 41.4 kB | | 4964748a |
| prm_trainer.html | 118 kB | | 4fa503d6 |
| prm_trainer.md | 13.9 kB | | 1f53e6da |
| ptt_integration.html | 29.3 kB | | 30735570 |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | 9300a370 |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 95.4 kB | | f34e875e |
| rapidfire_integration.md | 17.7 kB | | 08fed5af |
| reducing_memory_usage.html | 52.4 kB | | f8a29dec |
| reducing_memory_usage.md | 12.3 kB | | d61af82e |
|