| _app | | | 135 items |
| _toctree.yml | 3.29 kB | | 3ae9d845 |
| async_grpo_trainer.html | 108 kB | | b229a354 |
| async_grpo_trainer.md | 12.3 kB | | 69d98040 |
| bco_trainer.html | 130 kB | | 6f365cdc |
| bco_trainer.md | 14.1 kB | | 64448ec5 |
| bema_for_reference_model.html | 90 kB | | 26343293 |
| bema_for_reference_model.md | 7.18 kB | | 7ae69fc9 |
| callbacks.html | 95.8 kB | | 8a829586 |
| callbacks.md | 7.88 kB | | c656e4e0 |
| chat_template_utils.html | 45.5 kB | | 7f807d0b |
| chat_template_utils.md | 5.3 kB | | 0945b813 |
| clis.html | 53.4 kB | | 69ccfdd1 |
| clis.md | 12.8 kB | | f1e6c272 |
| community_tutorials.html | 31 kB | | 9e8bedf0 |
| community_tutorials.md | 11 kB | | 7d027f05 |
| cpo_trainer.html | 144 kB | | d09158ec |
| cpo_trainer.md | 23 kB | | 419b8f6e |
| customization.html | 31 kB | | 438f666e |
| customization.md | 4.08 kB | | 5962f8d3 |
| data_utils.html | 62.9 kB | | 845b04be |
| data_utils.md | 6.32 kB | | d9f30777 |
| dataset_formats.html | 223 kB | | 6f8d541e |
| dataset_formats.md | 40.2 kB | | d42b79a3 |
| deepspeed_integration.html | 15.8 kB | | 8ce9d26c |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distillation_trainer.html | 160 kB | | 932236f8 |
| distillation_trainer.md | 12.3 kB | | 2c71a3a5 |
| distributing_training.html | 96.5 kB | | 2f770f5e |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 232 kB | | 6fa12f9b |
| dpo_trainer.md | 30.8 kB | | 88f23679 |
| example_overview.html | 42.8 kB | | d1cb7bd2 |
| example_overview.md | 19.7 kB | | a2132bda |
| experimental_overview.html | 10.8 kB | | 851cc7ac |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 84.4 kB | | efb26430 |
| gfpo.md | 5.24 kB | | b0b5bea3 |
| gkd_trainer.html | 119 kB | | d93642f1 |
| gkd_trainer.md | 14.1 kB | | 9e8e87b2 |
| gold_trainer.html | 166 kB | | ad0ce082 |
| gold_trainer.md | 18.1 kB | | 7ac7309e |
| grpo_trainer.html | 559 kB | | d3614f3e |
| grpo_trainer.md | 55.2 kB | | 4967dc3a |
| grpo_with_replay_buffer.html | 89.6 kB | | 37791a48 |
| grpo_with_replay_buffer.md | 6.16 kB | | 4c9e14c7 |
| gspo_token.html | 50.2 kB | | 3ee3a8c8 |
| gspo_token.md | 4.27 kB | | df3891f1 |
| index.html | 29 kB | | a1a8d5cb |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | 1a46b8fe |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | 5cd92ed0 |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| kernels_hub.html | 26.8 kB | | 4c127beb |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 142 kB | | 63205f48 |
| kto_trainer.md | 18.4 kB | | 222ea743 |
| liger_kernel_integration.html | 15 kB | | b3bafb4a |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 836 kB | | 728d0cd3 |
| llms.txt | 5 kB | | a1292dea |
| lora_without_regret.html | 45 kB | | 67a14767 |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | f2db21b9 |
| merge_model_callback.md | 1.19 kB | | 372dce5d |
| minillm_trainer.html | 179 kB | | b62efc39 |
| minillm_trainer.md | 16.4 kB | | b1485dfd |
| nash_md_trainer.html | 124 kB | | c2ba4937 |
| nash_md_trainer.md | 16.3 kB | | 4381d91b |
| nemo_gym.html | 58.5 kB | | da5e5e8a |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.41 kB | | cc526ba8 |
| online_dpo_trainer.html | 179 kB | | 7d9eb421 |
| online_dpo_trainer.md | 23.1 kB | | e42bdc8d |
| openenv.html | 114 kB | | 7de36bd7 |
| openenv.md | 27.8 kB | | 3584ce48 |
| orpo_trainer.html | 127 kB | | e29480f9 |
| orpo_trainer.md | 17.7 kB | | 3e70ae74 |
| paper_index.html | 734 kB | | 23282db5 |
| paper_index.md | 19.1 kB | | 963e778f |
| papo_trainer.html | 111 kB | | 17a0ffe3 |
| papo_trainer.md | 8.82 kB | | fb876536 |
| peft_integration.html | 131 kB | | 3677e3dd |
| peft_integration.md | 23.9 kB | | 406031f7 |
| ppo_trainer.html | 278 kB | | 2cb57cf9 |
| ppo_trainer.md | 41.4 kB | | 3ee3d639 |
| prm_trainer.html | 117 kB | | 644cffc0 |
| prm_trainer.md | 13.9 kB | | 9a540b23 |
| ptt_integration.html | 29.3 kB | | 9939ce14 |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | 93d7c1ee |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 81.1 kB | | 1d0a65ac |
| rapidfire_integration.md | 12.8 kB | | 78b07e81 |
| reducing_memory_usage.html | 52.4 kB | | 41bdd9a3 |
| reducing_memory_usage.md | 12.3 kB | | d61af82e |
| reward_trainer.html | 175 kB | | ae74c81f |
| reward_trainer.md | 21.5 kB | | 8eb14643 |
|